© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 57600
    Prev
    Next
    INDEX
    Explanations

    statements or claims that are deemed false or misleading

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     basic
    -0.53
     basically
    -0.47
     essentially
    -0.47
     cross
    -0.46
     much
    -0.46
    BA
    -0.45
     post
    -0.44
     show
    -0.43
     mass
    -0.43
    basically
    -0.43
    POSITIVE LOGITS
    κτηρισ
    0.68
    ContentAsync
    0.68
     AssemblyCulture
    0.63
     CHAPITRE
    0.63
     ainfi
    0.63
     partagé
    0.62
     volando
    0.62
    Rüyada
    0.61
     murale
    0.60
     auffi
    0.60
    Activations Density 0.095%

    No Known Activations