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-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 3096
    Prev
    Next
    INDEX
    Explanations

    characters and symbols used in coding or digital representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gev
    -0.59
    Aholisi
    -0.48
    TagMode
    -0.47
     Италијани
    -0.47
    ScopeManager
    -0.44
    Diweddarwch
    -0.43
    RenderAtEndOf
    -0.42
    hake
    -0.42
     Bowers
    -0.42
    neté
    -0.42
    POSITIVE LOGITS
    omiast
    0.41
     gynnwys
    0.40
     kişinin
    0.40
     çift
    0.39
     Olsson
    0.38
     końca
    0.38
    siyon
    0.38
     clientId
    0.37
    eseorang
    0.36
     imageUrl
    0.35
    Activations Density 0.666%

    No Known Activations