© 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. 6604
    Prev
    Next
    INDEX
    Explanations

    themes related to powerful storytelling about human experiences and relationships

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

    Story/film about a journey or struggle

    np_acts-logits-general · gemini-2.0-flash

    characters' life journeys

    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
     venons
    -0.68
     supplémentaires
    -0.66
     ferons
    -0.63
     समीक्षाओं
    -0.62
    出版年
    -0.62
     mérite
    -0.62
     bénéfices
    -0.60
     supplémentaire
    -0.60
     réguli
    -0.59
    tizo
    -0.59
    POSITIVE LOGITS
     struggles
    0.82
     struggle
    0.82
     struggling
    0.74
     life
    0.65
     protagonist
    0.65
     characters
    0.64
     narrator
    0.63
     overcoming
    0.63
     claust
    0.62
     aftermath
    0.62
    Activations Density 0.308%

    No Known Activations