© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 12496
    Prev
    Next
    INDEX
    Explanations

    configuration parameters related to model optimization and performance tuning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.48
     صوتيه
    -0.39
    netje
    -0.37
     المكتبه
    -0.35
     للاسماء
    -0.35
     сложи
    -0.34
    orited
    -0.32
    rungsseite
    -0.32
    StatusCode
    -0.32
     autorytatywna
    -0.32
    POSITIVE LOGITS
     threshold
    1.00
     tolerance
    0.95
     thresholds
    0.77
     Tolerance
    0.76
     Threshold
    0.76
     tolerancia
    0.75
    threshold
    0.74
     tolerances
    0.73
     seed
    0.72
    tolerance
    0.71
    Activations Density 0.964%

    No Known Activations