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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 17-GEMMASCOPE-RES-16K
    6. 10793
    Prev
    Next
    INDEX
    Explanations

    technical terms and specifications related to scientific instrumentation and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    matmul
    -0.51
    rodalom
    -0.50
    walde
    -0.49
     >=",
    -0.48
    lub
    -0.45
    flan
    -0.45
    ilite
    -0.44
    jalna
    -0.44
    sidenav
    -0.44
     psicológica
    -0.43
    POSITIVE LOGITS
     capture
    0.90
     capturing
    0.85
     recording
    0.85
    capture
    0.84
     Capture
    0.83
    recording
    0.80
    采集
    0.78
    Capture
    0.77
     RECORDING
    0.74
     Recording
    0.74
    Activations Density 0.796%

    No Known Activations