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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 2322
    Prev
    Next
    INDEX
    Explanations

    elements related to media and technology references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ม้
    -0.49
     télé
    -0.46
     sven
    -0.46
    diep
    -0.45
    exist
    -0.45
    unque
    -0.44
    OrCreate
    -0.43
     gainera
    -0.43
     alone
    -0.42
    блица
    -0.42
    POSITIVE LOGITS
     дописавши
    0.71
    Portail
    0.69
     CommandType
    0.66
    Biographie
    0.64
    InvalidProtocol
    0.63
    annica
    0.63
    Abitanti
    0.61
    apunov
    0.61
     PartialEq
    0.61
    商品説明
    0.61
    Activations Density 1.635%

    No Known Activations