Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10654
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax specific to programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets or code-related terms

    np_acts-logits-general · gemini-2.0-flash

    programming languages keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.74
    httphttps
    -0.67
     Administrativna
    -0.63
     فريبيس
    -0.59
    IntoConstraints
    -0.58
    IsMutable
    -0.56
     intptr
    -0.55
     kasarigan
    -0.52
    ########.
    -0.49
    Aholisi
    -0.49
    POSITIVE LOGITS
     Freundin
    0.33
    <%=
    0.32
    PathVariable
    0.32
    
    0.31
    [:]
    0.30
    ganj
    0.30
    concurrent
    0.30
     herself
    0.30
     animals
    0.29
     FetchType
    0.29
    Activations Density 0.667%

    No Known Activations