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. 1178
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal policies and acts

    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
    ьаж
    -0.71
    SharedCtor
    -0.64
    참고
    -0.54
    IContainer
    -0.51
    いかが
    -0.49
     Italijanski
    -0.48
    SourceChecksum
    -0.44
    帖最后由
    -0.42
    kali
    -0.42
    المكان
    -0.41
    POSITIVE LOGITS
     writeTo
    0.67
     enacted
    0.66
     MotionEvent
    0.65
     SafeMath
    0.64
     vigente
    0.63
    SuppressMessage
    0.61
     governing
    0.60
    PhysRevD
    0.60
    partiet
    0.59
     Sections
    0.59
    Activations Density 0.549%

    No Known Activations