© 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. 9-GEMMASCOPE-RES-16K
    6. 8715
    Prev
    Next
    INDEX
    Explanations

    references to numeric data and statistical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OFDb
    -0.82
     AttributeSet
    -0.74
     arşivlendi
    -0.71
     propOrder
    -0.71
     المعيارى
    -0.69
    
    -0.67
    Diweddarwch
    -0.66
    Diwedd
    -0.61
     linkovi
    -0.60
    ſchaft
    -0.60
    POSITIVE LOGITS
     vol
    0.43
     Swanson
    0.36
     v
    0.35
    ,
    0.35
     Vol
    0.34
     as
    0.33
     “
    0.33
     extra
    0.32
    ;
    0.32
     an
    0.32
    Activations Density 0.334%

    No Known Activations