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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 2937
    Prev
    Next
    INDEX
    Explanations

    references to recycling programs or initiatives

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

    Mentions an "experiment", "model", or "program."

    np_acts-logits-general · gemini-2.0-flash

    programs, schemes, models, and policies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     föl
    -0.38
    Compiler
    -0.36
    Assertion
    -0.35
    cionais
    -0.35
     religieux
    -0.34
     botanical
    -0.34
     škoda
    -0.34
    verbindung
    -0.33
     Spazier
    -0.33
    rimônio
    -0.33
    POSITIVE LOGITS
     implemented
    1.02
     experiment
    0.99
     scheme
    0.94
     implementation
    0.94
     Implemented
    0.92
     experimented
    0.91
    implemented
    0.90
     experimento
    0.88
    experiment
    0.86
     experiments
    0.83
    Activations Density 0.768%

    No Known Activations