© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15156
    Prev
    Next
    INDEX
    Explanations

    questions regarding next steps or actions to take in a given situation.

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    medical and health-related information regarding breast density and associated laws and procedures.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases related to taking action or problem-solving, particularly focusing on variations of "what to do" or "what can be done" about a situation.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Follows "do" and indicates action

    np_acts-logits-general · gemini-2.0-flash

    do to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Massen
    -0.49
    avel
    -0.46
    Einzel
    -0.44
    IPO
    -0.44
    ginfo
    -0.43
    Sqft
    -0.42
    
    -0.42
    ')],
    -0.42
    Redacción
    -0.41
     Eastern
    -0.40
    POSITIVE LOGITS
    +:+
    0.83
     wrong
    0.82
     differently
    0.75
    enumii
    0.71
     åt
    0.69
    wrong
    0.69
    bootstrapcdn
    0.66
    MessageTagHelper
    0.65
    DoubleQuotes
    0.64
    SourceChecksum
    0.64
    Activations Density 0.131%

    No Known Activations