© 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-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 11202
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases associated with health risks, particularly regarding eating disorders and their consequences

    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
    posedge
    -0.54
     vợ
    -0.48
    новниш
    -0.48
     pending
    -0.47
    zionali
    -0.45
     кӀ
    -0.43
    ttä
    -0.43
    cza
    -0.43
    Noice
    -0.43
    áklad
    -0.42
    POSITIVE LOGITS
    orexia
    0.86
     suicidal
    0.84
     suicide
    0.81
    SequentialGroup
    0.76
     suicides
    0.72
     anorexia
    0.69
     dangerously
    0.68
     endangering
    0.68
     obsession
    0.67
     bleach
    0.67
    Activations Density 0.278%

    No Known Activations