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. 18-GEMMASCOPE-RES-16K
    6. 2212
    Prev
    Next
    INDEX
    Explanations

    references to medical directives and end-of-life wishes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comes before a quotation mark or attribution

    np_acts-logits-general · gemini-2.0-flash

    reports statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.63
    StoryboardSegue
    -0.60
    tvguidetime
    -0.59
    PMailer
    -0.59
     thereto
    -0.57
     Thus
    -0.56
    revet
    -0.54
     endwhile
    -0.54
     hitherto
    -0.52
     („
    -0.52
    POSITIVE LOGITS
     says
    0.79
    CloseOperation
    0.70
     say
    0.68
     tonight
    0.67
    says
    0.64
     SAYS
    0.63
     dicen
    0.60
    ernalia
    0.59
    LATEST
    0.56
     domani
    0.56
    Activations Density 0.089%

    No Known Activations