© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1350
    Prev
    Next
    INDEX
    Explanations

    organizational and procedural terms related to governance and scientific processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    production or transformation

    np_acts-logits-general · gemini-2.0-flash

    formation and production

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endpush
    -0.42
    tangentMode
    -0.41
     HasFactory
    -0.40
    jooq
    -0.38
     Newtonsoft
    -0.33
     TextInputType
    -0.33
     dran
    -0.32
    aile
    -0.32
    "]];
    -0.31
    featureID
    -0.31
    POSITIVE LOGITS
     forming
    0.80
     creating
    0.77
     membentuk
    0.74
     producing
    0.71
     transforming
    0.69
     produces
    0.63
     create
    0.63
     creates
    0.62
     converting
    0.62
     transforms
    0.60
    Activations Density 1.087%

    No Known Activations