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. 9-GEMMASCOPE-RES-16K
    6. 15667
    Prev
    Next
    INDEX
    Explanations

    terms related to file upload processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sites
    -0.73
    ****************
    -0.71
     atsi
    -0.71
     sites
    -0.70
    pra
    -0.70
    비스
    -0.69
     SITES
    -0.68
    jMenu
    -0.67
    Trouble
    -0.67
    adone
    -0.66
    POSITIVE LOGITS
     Broad
    0.96
     BROAD
    0.92
     Brod
    0.92
     transmite
    0.90
     Broadcast
    0.87
    SerializeField
    0.86
     transmitir
    0.86
    Broadcast
    0.85
    Broad
    0.84
     ब्रेकडाउन
    0.84
    Activations Density 0.150%

    No Known Activations