© 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. 2374
    Prev
    Next
    INDEX
    Explanations

    actions and processes related to execution or performance

    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
     queſta
    -1.07
     Geſch
    -0.98
    GEBURTSDATUM
    -0.97
     beſte
    -0.93
     beſch
    -0.92
    ſſung
    -0.91
     ſind
    -0.91
    Jeografia
    -0.90
    ſehen
    -0.90
    <unused16>
    -0.88
    POSITIVE LOGITS
     perform
    1.17
     performance
    0.92
    perform
    0.90
     performs
    0.87
     performing
    0.87
     Performance
    0.84
     Perform
    0.84
     please
    0.79
     performed
    0.75
     performances
    0.74
    Activations Density 0.365%

    No Known Activations