© 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. 18-GEMMASCOPE-RES-16K
    6. 9531
    Prev
    Next
    INDEX
    Explanations

    symbols and special characters commonly used in written text

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

    Something/Something else pattern

    np_acts-logits-general · gemini-2.0-flash

    word/word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.70
    .
    -0.65
     of
    -0.65
     in
    -0.63
    :
    -0.60
     to
    -0.60
    </i>
    -0.59
     —
    -0.57
     a
    -0.51
     tanto
    -0.50
    POSITIVE LOGITS
     للمعارف
    1.11
    %/
    1.07
     pleaſure
    1.07
    {}/
    1.07
    /=
    1.04
     purpoſe
    1.03
    ={`/
    1.00
     ?>/
    0.99
     greateſt
    0.99
    IndentedString
    0.98
    Activations Density 0.119%

    No Known Activations