© 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. 0-GEMMASCOPE-RES-16K
    6. 9841
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to loops and iteration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.57
     CURIAM
    -0.54
    writeFieldEnd
    -0.51
    PasswordField
    -0.51
     Reisedaten
    -0.51
    hols
    -0.48
     censiti
    -0.48
    ⟬
    -0.48
    qrstuvwxyz
    -0.48
    iented
    -0.47
    POSITIVE LOGITS
    parsedMessage
    0.53
     bride
    0.51
     loop
    0.49
     suits
    0.49
     lawsuits
    0.45
    <bos>
    0.45
    pu
    0.43
    loop
    0.43
     AssemblyVersion
    0.43
    logger
    0.43
    Activations Density 0.205%

    No Known Activations