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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 2125
    Prev
    Next
    INDEX
    Explanations

    function declarations and their characteristics

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

    constructor initializer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    providedIn
    -0.59
    +:+
    -0.53
    isContained
    -0.45
     MediatR
    -0.45
    enderror
    -0.45
     okuyayım
    -0.43
    AddTagHelper
    -0.43
    Билгалдахарш
    -0.42
    -------------</
    -0.41
    Kjelder
    -0.40
    POSITIVE LOGITS
    šanai
    0.46
    asyarakat
    0.45
    ļas
    0.44
     vayas
    0.41
    fill
    0.40
     Komun
    0.40
    aragus
    0.40
    gilan
    0.39
    ᵕ
    0.39
    érard
    0.39
    Activations Density 0.004%

    No Known Activations