Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 35
    Prev
    Next
    INDEX
    Explanations

    themes related to relationships and emotional connections in narratives

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

    Following tokens like "series", "films", "episodes", or "games"

    np_acts-logits-general · gemini-2.0-flash

    greatest films, games, series, or moments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KommentareTeilen
    -0.82
    ')")
    -0.82
    }}^{(
    -0.75
    '])->
    -0.74
    uxxxx
    -0.73
    AddTagHelper
    -0.71
     فريبيس
    -0.69
    jectures
    -0.69
    })`
    -0.68
    SequentialGroup
    -0.68
    POSITIVE LOGITS
     classic
    0.78
     classics
    0.73
    classic
    0.68
     timeless
    0.68
     iconic
    0.67
     seminal
    0.66
    iconic
    0.64
     underrated
    0.63
     legendary
    0.60
     memorable
    0.60
    Activations Density 0.283%

    No Known Activations