© 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. 35-GEMMASCOPE-RES-16K
    6. 14535
    Prev
    Next
    INDEX
    Explanations

    code structure and specific import statements in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.66
     HttpNotFound
    -0.66
     betweenstory
    -0.63
    يكب
    -0.63
     समीक्षाओं
    -0.63
    ValueStyle
    -0.61
     ویکی‌پدیا
    -0.60
    MockBean
    -0.59
    UrlResolution
    -0.57
    principalTable
    -0.55
    POSITIVE LOGITS
     TestBed
    0.42
    Application
    0.36
     OnInit
    0.36
     Injectable
    0.34
    Angel
    0.33
     Auss
    0.33
    TestBase
    0.32
    flutter
    0.32
     ogen
    0.31
    createClass
    0.31
    Activations Density 0.183%

    No Known Activations