© 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. 13-GEMMASCOPE-RES-16K
    6. 8122
    Prev
    Next
    INDEX
    Explanations

    comparisons of performance metrics and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    calaureate
    -0.50
    +#+
    -0.46
     Italijanski
    -0.45
    msgTypes
    -0.45
    るま
    -0.44
    cemia
    -0.44
     dada
    -0.44
     Allociné
    -0.44
     Pandora
    -0.44
    saf
    -0.44
    POSITIVE LOGITS
     improvement
    0.60
     improvements
    0.56
     mejora
    0.55
     mejoras
    0.52
     improved
    0.52
     verbess
    0.52
     improve
    0.52
     voordeel
    0.51
     difference
    0.50
    amélioration
    0.49
    Activations Density 1.356%

    No Known Activations