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. 8539
    Prev
    Next
    INDEX
    Explanations

    discussions about the future implications and potential directions for research

    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
    AnimationsModule
    -0.78
     AssemblyCulture
    -0.65
    RuleContext
    -0.64
    Попис
    -0.54
    Życiorys
    -0.53
     déroule
    -0.53
    ⁡
    -0.52
    PyExc
    -0.52
     dépend
    -0.52
    хіво
    -0.52
    POSITIVE LOGITS
     future
    1.35
    future
    1.25
    Future
    1.16
     Future
    1.09
     FUTURE
    1.01
    FUTURE
    0.94
     futuro
    0.93
    今後の
    0.93
    今後
    0.89
    avenir
    0.85
    Activations Density 0.742%

    No Known Activations