© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 7108
    Prev
    Next
    INDEX
    Explanations

    words related to health risks and awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存于互联网档案馆
    -0.75
    AndEndTag
    -0.74
     noDo
    -0.74
     useAppContext
    -0.71
    ArgsConstructor
    -0.67
    AntiForgeryToken
    -0.66
     Numerade
    -0.66
     disambiguazione
    -0.66
    Rüyada
    -0.65
     Chwiliwch
    -0.64
    POSITIVE LOGITS
     Bearing
    0.56
    Bearing
    0.52
     equally
    0.51
     bearing
    0.51
    having
    0.48
    bearing
    0.47
     cru
    0.46
     Equally
    0.45
     having
    0.45
    Whilst
    0.44
    Activations Density 0.283%

    No Known Activations