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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 73443
    Prev
    Next
    INDEX
    Explanations

    educational resources related to indigenous history and culture

    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_20/width_131k/average_l0_114
    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
     emphasized
    -0.35
     the
    -0.31
     álcool
    -0.31
     a
    -0.31
     suis
    -0.30
     of
    -0.30
     badly
    -0.29
     emphasize
    -0.29
     therein
    -0.29
     e
    -0.28
    POSITIVE LOGITS
     kasarigan
    0.76
    دانشنامهٔ
    0.65
    inkl
    0.60
    ⤹
    0.60
    aarrggbb
    0.59
    AISSEE
    0.59
    Personendaten
    0.59
     &___
    0.59
    windowFixed
    0.59
    Skocz
    0.58
    Activations Density 0.001%

    No Known Activations