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. 20-GEMMASCOPE-RES-16K
    6. 15552
    Prev
    Next
    INDEX
    Explanations

    elements related to immersive reading experiences and emotional engagement with characters

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

    Takes the reader/you on a journey/trip

    np_acts-logits-general · gemini-2.0-flash

    being immersed in a story

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.63
     AssemblyTitle
    -0.60
    hasNext
    -0.56
     ब्रेकडाउन
    -0.56
     estekak
    -0.55
    पया
    -0.54
    انيف
    -0.54
     isNameExpr
    -0.53
    ConstraintMaker
    -0.52
     actualité
    -0.52
    POSITIVE LOGITS
     immersion
    1.15
     immersed
    1.07
     immerse
    1.07
     immers
    1.05
     Immer
    1.03
     transports
    1.03
     transported
    1.02
     Immersion
    0.98
     transport
    0.97
    immer
    0.93
    Activations Density 0.208%

    No Known Activations