© 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
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 7493
    Prev
    Next
    INDEX
    Explanations

    specific references to institutions or entities associated with 'UC' or 'Luk'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ponses
    -0.32
    <h5>
    -0.31
    الدراسه
    -0.28
     Zeichen
    -0.28
     voci
    -0.28
    ˉ
    -0.28
     متعلقه
    -0.28
    delwed
    -0.28
    ティン
    -0.27
    ksikon
    -0.27
    POSITIVE LOGITS
    ChildScrollView
    0.67
    TemporalType
    0.61
    
    0.61
     Nuk
    0.54
     NUC
    0.54
     NUK
    0.54
    Autoritní
    0.54
    writeField
    0.54
     Ruk
    0.54
    aarrggbb
    0.53
    Activations Density 0.200%

    No Known Activations