© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 111157
    Prev
    Next
    INDEX
    Explanations

    phrases related to familiarity and understanding in various contexts

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

    reflexive pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     createState
    -0.51
    GTCX
    -0.49
    EDEFAULT
    -0.48
     intptr
    -0.43
    ⓘ
    -0.42
     cejas
    -0.41
     numerus
    -0.40
    )});
    -0.40
     aceptas
    -0.40
    Importante
    -0.40
    POSITIVE LOGITS
     yourself
    0.85
     Yourself
    0.77
     oneself
    0.76
    yourself
    0.72
     ourselves
    0.71
    himself
    0.71
     myself
    0.69
     himself
    0.68
     yourselves
    0.67
    myself
    0.66
    Activations Density 0.024%

    No Known Activations