© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 6643
    Prev
    Next
    INDEX
    Explanations

    syntax elements and constructs related to programming, such as brackets, semicolons, and function calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.82
    AndEndTag
    -0.75
    tagHelperRunner
    -0.71
    rungsseite
    -0.68
    AddTagHelper
    -0.66
    MessageTagHelper
    -0.64
     nahilalakip
    -0.63
     createState
    -0.57
    MergeFrom
    -0.57
     myſelf
    -0.56
    POSITIVE LOGITS
    sizeCache
    0.40
    Viungo
    0.36
     الرياضيه
    0.35
    significant
    0.33
    Sprintf
    0.33
    ```
    
    0.32
    menso
    0.32
    strncmp
    0.32
     isNameExpr
    0.32
    ۣ
    0.31
    Activations Density 0.322%

    No Known Activations