Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 74351
    Prev
    Next
    INDEX
    Explanations

    references to social sciences and related concepts

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

    Social fields and professions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    它們
    -0.66
    +#+#
    -0.63
    argout
    -0.60
    BeginContext
    -0.59
     للمعارف
    -0.58
    AnchorStyles
    -0.57
     dragón
    -0.57
    它们
    -0.56
     ejército
    -0.56
    corazón
    -0.54
    POSITIVE LOGITS
     Social
    0.69
    Social
    0.54
     SOCIAL
    0.44
    PSY
    0.39
     dial
    0.38
    Random
    0.38
     Pseudo
    0.38
     auto
    0.38
     PSY
    0.38
     pseudo
    0.37
    Activations Density 0.010%

    No Known Activations