© 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. 33-GEMMASCOPE-RES-16K
    6. 11686
    Prev
    Next
    INDEX
    Explanations

    instances of numerical 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 @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Initializes
    -0.32
    Vanjske
    -0.30
     FetchType
    -0.29
    SuspendLayout
    -0.28
     sn
    -0.27
     mystery
    -0.26
    (`
    -0.26
     present
    -0.26
    vaient
    -0.26
    ыгана
    -0.24
    POSITIVE LOGITS
    rungsseite
    0.74
    Tembelea
    0.73
     disambiguazione
    0.71
    httphttps
    0.69
     ProtoMessage
    0.66
     defaultstate
    0.62
    
    0.60
     للاسماء
    0.60
     الحره
    0.59
    ########.
    0.59
    Activations Density 0.171%

    No Known Activations