Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 12-GEMMASCOPE-RES-16K
    6. 1547
    Prev
    Next
    INDEX
    Explanations

    states of unconsciousness or death

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.53
     שוליים
    -0.51
     aikaa
    -0.46
     كومونز
    -0.46
    спе
    -0.46
     tiêu
    -0.45
     speciality
    -0.45
     Emphasis
    -0.44
     themes
    -0.44
     ligiloj
    -0.43
    POSITIVE LOGITS
    Datuak
    0.71
     ölü
    0.69
     motionless
    0.68
     dead
    0.66
     asleep
    0.64
     мерт
    0.64
     frozen
    0.61
     مرئيه
    0.60
     standstill
    0.60
    dead
    0.59
    Activations Density 0.274%

    No Known Activations