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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15785
    Prev
    Next
    INDEX
    Explanations

    elements related to graphical components and their coordinates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    queryInterface
    -0.89
    UrlResolution
    -0.82
    LookAnd
    -0.79
     سكانية
    -0.78
     nakalista
    -0.77
    AddTagHelper
    -0.75
    ReusableCell
    -0.73
    featureID
    -0.71
    WriteTagHelper
    -0.71
     contextLoads
    -0.71
    POSITIVE LOGITS
    ソッド
    0.34
     Reisen
    0.33
    cza
    0.32
    <eos>
    0.31
     vs
    0.31
    <b>
    0.31
    ?,
    0.31
     results
    0.30
     Silber
    0.30
     weaves
    0.30
    Activations Density 0.860%

    No Known Activations