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
    4. Residual Stream - 131k
    5. 23-GEMMASCOPE-RES-131K
    6. 65
    Prev
    Next
    INDEX
    Explanations

    code segments, particularly those involving imports and method definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kept
    -0.29
     instead
    -0.28
     gratuites
    -0.28
     armées
    -0.27
     held
    -0.27
     istället
    -0.27
     întâ
    -0.27
    conexao
    -0.27
     fapt
    -0.26
     пой
    -0.26
    POSITIVE LOGITS
     يتيمه
    0.86
    KommentareTeilen
    0.77
    RenderAtEndOf
    0.74
    OGND
    0.72
     ویکی‌پدی
    0.71
    tagHelperRunner
    0.70
    RTEX
    0.68
    principalColumn
    0.67
     betweenstory
    0.66
     transfieras
    0.66
    Activations Density 0.010%

    No Known Activations