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. 8-GEMMASCOPE-RES-16K
    6. 4793
    Prev
    Next
    INDEX
    Explanations

    content related to contests and winner announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Попис
    -0.79
    ContentAlignment
    -0.76
    ValueStyle
    -0.71
    URLException
    -0.70
    WithIOException
    -0.67
     createSprite
    -0.63
    ModelSerializer
    -0.62
    ambilan
    -0.62
    iddhar
    -0.61
     Савезне
    -0.60
    POSITIVE LOGITS
     submissions
    0.65
     feedback
    0.64
     Submissions
    0.58
    feedback
    0.57
     Feedback
    0.56
    Feedback
    0.51
     responses
    0.49
    Izvori
    0.49
    Submissions
    0.49
    ysł
    0.48
    Activations Density 0.164%

    No Known Activations