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. 17-GEMMASCOPE-RES-16K
    6. 7117
    Prev
    Next
    INDEX
    Explanations

    references to articles and reports related to current events or studies

    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
    aarrggbb
    -0.79
     createState
    -0.78
    expandindo
    -0.67
    ContentAsync
    -0.64
     Patro
    -0.63
    CGRectMake
    -0.62
    UnsafeEnabled
    -0.61
    tagez
    -0.58
     acque
    -0.57
    Jereo
    -0.57
    POSITIVE LOGITS
     article
    0.89
     video
    0.89
     recent
    0.81
     blog
    0.75
    älde
    0.60
     letter
    0.59
     report
    0.58
     artikel
    0.57
     YouTube
    0.57
    recent
    0.56
    Activations Density 0.550%

    No Known Activations