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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 7503
    Prev
    Next
    INDEX
    Explanations

    callback-related terms in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 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
     AssemblyTitle
    -0.63
     en
    -0.63
     Le
    -0.61
     har
    -0.59
     v
    -0.59
     le
    -0.56
     das
    -0.55
     Mc
    -0.54
     ch
    -0.54
    üe
    -0.54
    POSITIVE LOGITS
     myſelf
    1.10
     themſelves
    1.06
     purpoſe
    1.06
     houſe
    1.04
     Theſe
    1.02
     Efq
    1.00
     Anſ
    0.98
     ―――――
    0.96
     ſtate
    0.95
     Majefty
    0.95
    Activations Density 0.091%

    No Known Activations