© 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. 7959
    Prev
    Next
    INDEX
    Explanations

    evaluative phrases about success and failure in various contexts

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

    after "commercial" or "been"

    np_acts-logits-general · gemini-2.0-flash

    commercial and business success

    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
    \{\\
    -0.74
    EndContext
    -0.73
    __':
    -0.70
    DOCTYPE
    -0.69
    ]")]
    -0.69
    reactstrap
    -0.66
    __':
    -0.65
    CrossRef
    -0.63
    DotNetBar
    -0.62
     متعلقه
    -0.62
    POSITIVE LOGITS
     success
    3.15
     successful
    2.93
    success
    2.69
     Success
    2.62
     SUCCESS
    2.55
    Success
    2.54
     Successful
    2.48
    successful
    2.48
     succès
    2.37
     sucess
    2.34
    Activations Density 0.423%

    No Known Activations