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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 108448
    Prev
    Next
    INDEX
    Explanations

    references to journalism and reporting

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

    journalists and reporters

    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
    UrlResolution
    -0.56
    queryInterface
    -0.41
    posedge
    -0.36
     المرجع
    -0.35
    évaluateur
    -0.35
    paramref
    -0.33
    astify
    -0.33
    PositiveButton
    -0.32
     poveznice
    -0.31
    ebvre
    -0.30
    POSITIVE LOGITS
    journalist
    0.75
     journalist
    0.71
     journalistic
    0.70
     reporter
    0.69
     journalism
    0.67
     journalists
    0.66
    reporter
    0.65
     reporters
    0.63
    Journalist
    0.63
     Journalists
    0.59
    Activations Density 0.043%

    No Known Activations