© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 11145
    Prev
    Next
    INDEX
    Explanations

    expressions of strong emotion or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -1.02
    AndEndTag
    -1.02
    oredCriteria
    -0.99
    featureID
    -0.97
     للمعارف
    -0.96
     NSCoder
    -0.96
    出版年
    -0.92
     estekak
    -0.92
     Normdatei
    -0.91
     Drapeau
    -0.91
    POSITIVE LOGITS
    ________________
    0.72
    (
    0.69
    ================
    0.69
    ----------------
    0.66
                                   
    0.63
    I
    0.60
    In
    0.60
    http
    0.58
    This
    0.56
    The
    0.56
    Activations Density 1.035%

    No Known Activations