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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5455
    Prev
    Next
    INDEX
    Explanations

    phrases related to seeking additional information

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

    Preceding "information" or "info"

    np_acts-logits-general · gemini-2.0-flash

    more information

    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
    نجليز
    -0.52
    Gesamt
    -0.51
     esboço
    -0.50
    لكتر
    -0.49
     most
    -0.49
     pylint
    -0.48
     full
    -0.48
    Diwedd
    -0.47
    again
    -0.47
    encore
    -0.46
    POSITIVE LOGITS
     information
    0.83
    fromnode
    0.80
     about
    0.74
    RegistryLite
    0.68
    information
    0.66
    Sucesor
    0.64
    setVerticalGroup
    0.63
     ExecuteAsync
    0.62
     info
    0.62
    ArgsConstructor
    0.61
    Activations Density 0.079%

    No Known Activations