Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 10286
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions related to ratios and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.76
    transQ
    -0.69
    MLLoader
    -0.69
    sizeCache
    -0.68
     يتيمه
    -0.68
     $_"
    -0.66
    expandindo
    -0.64
     queſta
    -0.63
     Мексичка
    -0.63
    ⟬
    -0.60
    POSITIVE LOGITS
     Schrauben
    0.37
     screws
    0.33
    istung
    0.33
     its
    0.32
     Simpson
    0.31
    STELL
    0.31
     Hoffman
    0.30
     segar
    0.30
    beho
    0.30
     unchanged
    0.30
    Activations Density 0.878%

    No Known Activations