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. 1838
    Prev
    Next
    INDEX
    Explanations

    references to political or legal authority and discussions around judicial matters

    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
    djangoproject
    -0.65
     NUKAT
    -0.61
    有点
    -0.59
    หน่อย
    -0.56
    monials
    -0.56
     biraz
    -0.56
     underestimated
    -0.56
     PAN
    -0.55
    PAN
    -0.55
    Beijinhos
    -0.55
    POSITIVE LOGITS
     clearly
    0.75
     centaines
    0.74
     hundreds
    0.69
     jelas
    0.68
     countless
    0.66
    clearly
    0.64
    hundreds
    0.63
     already
    0.63
     thousands
    0.63
    又不是
    0.63
    Activations Density 0.870%

    No Known Activations