© 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. 9-GEMMASCOPE-RES-16K
    6. 14900
    Prev
    Next
    INDEX
    Explanations

    the beginning of a document or section

    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
    انتهای
    -0.63
     ex
    -0.61
    *~*~
    -0.58
     explo
    -0.58
     gl
    -0.56
     $=-
    -0.55
    ixeira
    -0.54
    .%
    -0.53
    aville
    -0.53
    (${
    -0.53
    POSITIVE LOGITS
    <bos>
    0.76
     nessuna
    0.69
     supérieures
    0.67
     gostar
    0.67
     producteurs
    0.66
     rodea
    0.64
     temprana
    0.61
     varandra
    0.61
     nenhuma
    0.60
     nessuno
    0.60
    Activations Density 0.550%

    No Known Activations