© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 7719
    Prev
    Next
    INDEX
    Explanations

    references to scoring metrics and performance evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ziegler
    -0.54
     Jimenez
    -0.52
     Plan
    -0.46
     Sib
    -0.44
     Fully
    -0.44
     Oude
    -0.44
     Dubois
    -0.44
     new
    -0.43
     Chapman
    -0.42
    LoggerFactory
    -0.42
    POSITIVE LOGITS
     score
    1.97
     Score
    1.85
    score
    1.78
    Score
    1.71
     scores
    1.60
     Scores
    1.57
     scoring
    1.55
    SCORE
    1.52
     SCORE
    1.52
     scored
    1.47
    Activations Density 0.102%

    No Known Activations