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. 24-GEMMASCOPE-RES-131K
    6. 969
    Prev
    Next
    INDEX
    Explanations

    elements related to programming concepts and syntax

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

    executing actions and sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    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
    -0.75
    ChildScrollView
    -0.67
    ReusableCell
    -0.63
    MessageTagHelper
    -0.59
     utafitiHapana
    -0.59
    ergies
    -0.57
    outSlope
    -0.56
    ngrx
    -0.55
     Autorizaciones
    -0.55
    الحياه
    -0.53
    POSITIVE LOGITS
     wearing
    0.39
     uitvo
    0.38
     executar
    0.37
     duração
    0.36
    bonucle
    0.36
     realização
    0.36
    ebenarnya
    0.34
     measure
    0.33
     execução
    0.33
     direta
    0.33
    Activations Density 0.125%

    No Known Activations