© 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-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 2484
    Prev
    Next
    INDEX
    Explanations

    expressions related to frequency or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.88
    MessageOf
    -0.87
     ProtoMessage
    -0.87
    ########.
    -0.86
    adaptiveStyles
    -0.86
     للاسماء
    -0.82
     يتيمه
    -0.82
    rungsseite
    -0.82
    GEBURTSDATUM
    -0.80
    SharedDtor
    -0.79
    POSITIVE LOGITS
     fantastic
    0.59
     lot
    0.57
     lots
    0.56
     fabulous
    0.50
     Fantastic
    0.49
     pretty
    0.49
     quoted
    0.47
     more
    0.46
     quotes
    0.45
     terrific
    0.45
    Activations Density 0.350%

    No Known Activations