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 - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 33899
    Prev
    Next
    INDEX
    Explanations

    structure and syntax in code snippets, particularly focusing on class and method definitions

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

    code generation, swagger, tool

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Бахар
    -0.48
    EDEFAULT
    -0.46
     برانيه
    -0.46
    antMatchers
    -0.45
    ImageContext
    -0.45
    +:+
    -0.44
    Therapeutic
    -0.43
     microbiota
    -0.43
    InitStruct
    -0.42
    zzleHttp
    -0.41
    POSITIVE LOGITS
    endmodule
    0.46
    __()
    0.41
    ills
    0.40
    close
    0.40
     close
    0.36
    MockBean
    0.35
    :✨
    0.35
    zusetzen
    0.35
    FormTagHelper
    0.35
    hours
    0.34
    Activations Density 0.004%

    No Known Activations