© 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. 3070
    Prev
    Next
    INDEX
    Explanations

    references to SQL and related database operations

    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
     Circle
    -0.65
     Race
    -0.63
     circle
    -0.60
     Nap
    -0.54
     box
    -0.54
     nahilalakip
    -0.54
     tube
    -0.54
     Challenge
    -0.53
     CIRCLE
    -0.53
     insert
    -0.53
    POSITIVE LOGITS
    Soft
    0.95
    Software
    0.91
     Software
    0.85
     Soft
    0.84
     SOFT
    0.73
     SOFTWARE
    0.72
    soft
    0.68
    SOFT
    0.68
     logiciels
    0.66
     ソフト
    0.65
    Activations Density 0.164%

    No Known Activations