© 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. 18-GEMMASCOPE-RES-16K
    11. 4069
    Prev
    Next
    INDEX
    Explanations

    elements of emotional expression and character development in reviews

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

    Elements of suspenseful stories

    np_acts-logits-general · gemini-2.0-flash

    plot and suspense elements

    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
    tvguidetime
    -0.73
    LookAnd
    -0.67
     otomatig
    -0.66
     nonUne
    -0.64
     "/")
    -0.63
     betreft
    -0.57
    !*\
    -0.57
    Gruß
    -0.56
     enregistré
    -0.55
    ponses
    -0.55
    POSITIVE LOGITS
     suspense
    1.02
     plot
    0.88
     tension
    0.81
     reader
    0.77
     Spannung
    0.73
    Suspense
    0.73
     foreshadow
    0.72
     readers
    0.69
     climax
    0.69
     PLOT
    0.69
    Activations Density 0.302%

    No Known Activations