© 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. 21-GEMMASCOPE-RES-16K
    11. 15786
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation, indicating it focuses on structural elements in text

    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
     myſelf
    -0.37
     ſtand
    -0.36
    wachs
    -0.35
    strokeColor
    -0.34
    ſelf
    -0.33
    mPaint
    -0.33
     vendors
    -0.32
     enth
    -0.32
     Deckel
    -0.32
     faſt
    -0.32
    POSITIVE LOGITS
    oa̍t
    0.75
    تقاوى
    0.74
     OMITBAD
    0.62
     pinulongan
    0.60
    SharedCtor
    0.60
     cherchés
    0.59
     nahilalakip
    0.58
    uxxxx
    0.58
    Tikang
    0.56
    writeFieldEnd
    0.56
    Activations Density 1.685%

    No Known Activations