© 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 - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15934
    Prev
    Next
    INDEX
    Explanations

    numerical data and associated scientific terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.97
    存于互联网档案馆
    -0.74
    piac
    -0.68
    versy
    -0.67
    CloseOperation
    -0.65
     bodyParser
    -0.63
    

    -0.63
    urka
    -0.61
    ือง
    -0.61
    ')}
    -0.60
    POSITIVE LOGITS
     Majefty
    0.83
     popoli
    0.78
    ként
    0.74
     belangrij
    0.72
    PreExecute
    0.71
     ſtate
    0.70
     neceff
    0.69
     KML
    0.67
     Jefus
    0.67
     nõ
    0.67
    Activations Density 0.730%

    No Known Activations