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-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 9425
    Prev
    Next
    INDEX
    Explanations

    indicators of the use of programming languages or frameworks in code documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MENAFN
    -0.57
    uxxxx
    -0.57
    }{*}{
    -0.57
    principalColumn
    -0.56
     فريبيس
    -0.54
    Kjelder
    -0.54
     EconPapers
    -0.52
     gynhyrchwyd
    -0.52
     nakalista
    -0.52
     Réalisation
    -0.51
    POSITIVE LOGITS
     disable
    1.73
     Disable
    1.43
    disable
    1.42
    Disable
    1.36
     disabling
    1.15
     disables
    1.09
     DISABLE
    0.98
     Enable
    0.92
     disabled
    0.86
     deactivate
    0.85
    Activations Density 0.012%

    No Known Activations