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
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6035
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries related to opinions, decisions, and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ceğine
    -0.36
    irited
    -0.33
    RTGC
    -0.33
     pstmt
    -0.31
    devamını
    -0.30
     Процитовано
    -0.30
     dzie
    -0.29
    scriptId
    -0.28
    Crossref
    -0.28
     chì
    -0.28
    POSITIVE LOGITS
    SequentialGroup
    0.85
    出版年
    0.64
    DockStyle
    0.63
    AnchorStyles
    0.60
     kasarigan
    0.59
    HandlerContext
    0.57
    SupportActionBar
    0.56
    JAMIN
    0.55
    HomeAsUpEnabled
    0.54
     InputDecoration
    0.53
    Activations Density 0.645%

    No Known Activations