© 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. 21-GEMMASCOPE-RES-16K
    6. 2555
    Prev
    Next
    INDEX
    Explanations

    date-related information or attributes within a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wymiar
    -0.38
     tričko
    -0.38
     Erişim
    -0.38
    ectady
    -0.37
     wünschen
    -0.34
     запе
    -0.33
     Ży
    -0.33
     propriétaires
    -0.33
     Authors
    -0.33
     attes
    -0.32
    POSITIVE LOGITS
    AddTagHelper
    0.58
    enterOuterAlt
    0.58
    buttonShape
    0.54
    CopyWith
    0.54
    getMonth
    0.53
    +:+
    0.52
    تقاوى
    0.49
     يتيمه
    0.47
    tagHelperRunner
    0.47
    ViewById
    0.45
    Activations Density 0.125%

    No Known Activations