© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 1994
    Prev
    Next
    INDEX
    Explanations

    numerical statistics and accolades related to athletic performance

    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
     مرئيه
    -0.65
    DockStyle
    -0.60
     doInBackground
    -0.59
    AutoresizingMask
    -0.59
     vectoriales
    -0.58
    batore
    -0.57
    )];
    -0.57
    ANNES
    -0.57
    apatos
    -0.55
    )}]{
    -0.54
    POSITIVE LOGITS
     boys
    0.59
     girls
    0.57
    Instruction
    0.52
     INSTRUCTION
    0.51
     trophies
    0.51
    StoreMessageInfo
    0.50
     Ceci
    0.50
     instructional
    0.49
    preventDefault
    0.48
    instruction
    0.48
    Activations Density 0.128%

    No Known Activations