© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 10470
    Prev
    Next
    INDEX
    Explanations

    terms related to physical marks or impressions

    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
    ynomial
    -0.39
     ſte
    -0.35
    ̈́
    -0.35
    ttemberg
    -0.34
    uaikan
    -0.34
     cauza
    -0.33
    PMailer
    -0.32
     محفوظة
    -0.32
    Equipo
    -0.32
    hematical
    -0.32
    POSITIVE LOGITS
     Bres
    0.59
    gun
    0.59
     foot
    0.57
     Owen
    0.56
     walk
    0.56
    foot
    0.54
    agi
    0.54
     Spar
    0.54
     strolling
    0.54
    zi
    0.53
    Activations Density 1.686%

    No Known Activations