© 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. 36-GEMMASCOPE-RES-16K
    6. 16068
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols used in technical writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doInBackground
    -0.51
    TargetException
    -0.47
    AndEndTag
    -0.46
     lâmpada
    -0.45
     desmotivaciones
    -0.45
    oneofs
    -0.45
     yaiba
    -0.44
     initComponents
    -0.43
     CURIAM
    -0.43
    endpush
    -0.42
    POSITIVE LOGITS
    Tikang
    0.56
    EndContext
    0.42
     NSCoder
    0.38
     GoogleFonts
    0.36
     advent
    0.36
    MLLoader
    0.34
     blessing
    0.34
    ={({
    0.34
    fir
    0.34
    ators
    0.34
    Activations Density 0.169%

    No Known Activations