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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 6474
    Prev
    Next
    INDEX
    Explanations

    elements related to programming code structure and dependencies

    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
    expandindo
    -0.64
     contextLoads
    -0.56
     ويكيميديا
    -0.53
    boe
    -0.51
    Jeografia
    -0.50
     handleMessage
    -0.50
     vt
    -0.48
     فريبيس
    -0.48
     werfen
    -0.48
    Nationale
    -0.47
    POSITIVE LOGITS
    WithIOException
    0.73
    rawDesc
    0.69
    Hints
    0.67
    ISupport
    0.66
     TestBed
    0.66
    ᅠ
    0.65
     Dubuque
    0.64
     Hint
    0.63
     bend
    0.62
     Hints
    0.61
    Activations Density 2.893%

    No Known Activations