© 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. 23-GEMMASCOPE-RES-16K
    6. 2304
    Prev
    Next
    INDEX
    Explanations

    phrases associated with strategies or methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.56
    gemaakt
    -0.49
     برانيه
    -0.48
     nakalista
    -0.48
     zelve
    -0.47
     goederen
    -0.46
     finanzas
    -0.46
     ulong
    -0.46
     statistique
    -0.46
    jsonwebtoken
    -0.45
    POSITIVE LOGITS
     approach
    1.35
     Approach
    1.30
    approach
    1.29
     APPROACH
    1.17
    Approach
    1.17
     approaches
    1.14
     Approaches
    0.98
     approached
    0.97
     approche
    0.91
    approche
    0.90
    Activations Density 0.121%

    No Known Activations