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. 103160
    Prev
    Next
    INDEX
    Explanations

    URLs and web address formatting

    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
     reducido
    -0.47
     enfans
    -0.43
     pauvres
    -0.42
     extranjera
    -0.42
     publiée
    -0.42
     cuyos
    -0.41
     dirigeants
    -0.40
     propuesto
    -0.40
     proposé
    -0.40
     dispuesto
    -0.40
    POSITIVE LOGITS
    ://$
    0.85
    ://
    0.84
    ://"
    0.76
    :///
    0.76
    URLException
    0.72
    XmlAccessType
    0.70
     '{@
    0.70
    ="@+
    0.70
     nakalista
    0.68
     Numerade
    0.67
    Activations Density 0.004%

    No Known Activations