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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 7470
    Prev
    Next
    INDEX
    Explanations

    numerical values, specifically focusing on the number 9

    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-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
    WriteTagHelper
    -0.37
    脚注の使い方
    -0.35
    yyv
    -0.34
    축
    -0.34
    消
    -0.34
    classnames
    -0.33
    mbrie
    -0.33
     NgModule
    -0.33
     Drittan
    -0.33
     flutter
    -0.33
    POSITIVE LOGITS
    contentLoaded
    0.55
    finally
    0.51
     finally
    0.47
    DockStyle
    0.44
     finalmente
    0.43
    principalTable
    0.43
     infine
    0.42
     Finally
    0.42
    phazard
    0.41
    EndInit
    0.40
    Activations Density 0.000%

    No Known Activations