© 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. 15-GEMMASCOPE-RES-16K
    6. 2591
    Prev
    Next
    INDEX
    Explanations

    attributes and descriptors related to products or features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.93
    RenderAtEndOf
    -0.91
    IntoConstraints
    -0.90
    Datuak
    -0.83
    OGND
    -0.80
     виправивши
    -0.71
     inalámb
    -0.71
    GEBURTSDATUM
    -0.70
     térm
    -0.69
     समीक्षाओं
    -0.68
    POSITIVE LOGITS
     
    0.49
     Dem
    0.46
     unique
    0.46
     wide
    0.46
     neutral
    0.43
    tuigen
    0.43
     home
    0.43
    '])->
    0.43
    API
    0.43
     “
    0.42
    Activations Density 0.450%

    No Known Activations