© 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. 4-GEMMASCOPE-RES-16K
    6. 12795
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and references to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     I
    -0.86
     me
    -0.85
     my
    -0.84
     myself
    -0.78
    我
    -0.76
    myself
    -0.73
     crossorigin
    -0.70
     Myself
    -0.70
    我的
    -0.69
    我和
    -0.68
    POSITIVE LOGITS
     preocupes
    0.64
    enterOuterAlt
    0.63
     hänen
    0.51
     actionMode
    0.51
     škoda
    0.49
     públicos
    0.48
     duradero
    0.48
     alimentaires
    0.46
     scolaires
    0.46
     kurie
    0.45
    Activations Density 0.287%

    No Known Activations