© 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. 25-GEMMASCOPE-RES-16K
    6. 15366
    Prev
    Next
    INDEX
    Explanations

    programming terminology related to server and coding configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nhat
    -0.39
    RTHOOK
    -0.39
     contrast
    -0.39
     Fuentes
    -0.35
     wash
    -0.35
     count
    -0.35
    <?
    -0.34
    polyline
    -0.34
     Eing
    -0.34
    des
    -0.34
    POSITIVE LOGITS
    createServer
    0.65
    ServerSocket
    0.61
    󠁣
    0.60
     houſe
    0.59
    getPort
    0.58
     portu
    0.58
    ClientSize
    0.57
     port
    0.56
     pleaſure
    0.55
     AppCompatTheme
    0.54
    Activations Density 0.215%

    No Known Activations