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. 15-GEMMASCOPE-RES-16K
    6. 12942
    Prev
    Next
    INDEX
    Explanations

    elements related to community support and collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FetchType
    -0.63
    potranspiration
    -0.60
    ]<<"
    -0.59
    出版年
    -0.59
     ***!
    -0.57
    tvguidetime
    -0.54
    :]:
    -0.54
    LayoutStyle
    -0.53
     Ubicación
    -0.52
     toujours
    -0.52
    POSITIVE LOGITS
     temporarily
    1.35
     momentarily
    1.20
     temporaire
    1.02
     briefly
    1.01
     temporary
    1.01
     tijde
    0.98
     momentary
    0.91
     Temporary
    0.90
    tempor
    0.88
    Temporary
    0.84
    Activations Density 0.240%

    No Known Activations