© 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-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 14550
    Prev
    Next
    INDEX
    Explanations

    mentions of callback functions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \{\\
    -0.70
    :✨
    -0.60
    SequentialGroup
    -0.59
    ïne
    -0.55
    holde
    -0.51
    msgTypes
    -0.49
    日閲覧
    -0.49
     فريبيس
    -0.47
    mallows
    -0.47
    zeitige
    -0.46
    POSITIVE LOGITS
    callback
    0.90
     callback
    0.83
     Callback
    0.72
    [/
    0.67
     comeback
    0.66
    Abitanti
    0.65
     additive
    0.65
    Indoor
    0.63
     Indoor
    0.63
    üyor
    0.62
    Activations Density 0.082%

    No Known Activations