© 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. 2677
    Prev
    Next
    INDEX
    Explanations

    programming and scripting constructs, particularly related to file handling and JSON processing

    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
    Personendaten
    -0.87
    +#+#
    -0.82
    Билгалдахарш
    -0.80
    ंदीखरीदारी
    -0.73
     الرياضيه
    -0.71
     تضيفلها
    -0.69
     ویکی‌پدی
    -0.68
    oa̍t
    -0.68
    verwijspagina
    -0.66
    AndEndTag
    -0.66
    POSITIVE LOGITS
    DataPropertyName
    0.36
     holen
    0.34
     abger
    0.34
     صنعتی
    0.33
    conne
    0.32
     actual
    0.32
     Conne
    0.31
    BitmapFactory
    0.31
    FetchType
    0.31
     scheinen
    0.30
    Activations Density 0.491%

    No Known Activations