© 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. 3140
    Prev
    Next
    INDEX
    Explanations

    programmatic elements and technical terminologies

    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
     bacio
    -0.35
     manzanas
    -0.35
     cuantos
    -0.35
    ecé
    -0.34
     figliu
    -0.31
     Boyce
    -0.31
     ため
    -0.31
     Apple
    -0.30
    География
    -0.30
     crimen
    -0.29
    POSITIVE LOGITS
     conch
    0.74
     dome
    0.66
     Survey
    0.62
     tent
    0.62
     Mall
    0.61
     banner
    0.59
     Surveys
    0.59
     Dome
    0.59
    Surveys
    0.58
    Plaza
    0.57
    Activations Density 1.970%

    No Known Activations