© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 8167
    Prev
    Next
    INDEX
    Explanations

    elements related to tension, suspense, and the emotional impact of storytelling

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

    Follows a punctuation mark

    np_acts-logits-general · gemini-2.0-flash

    end punctuation

    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
    非常的
    -0.78
     therefor
    -0.71
    Whilst
    -0.69
     definately
    -0.69
    Дан
    -0.68
    Anyways
    -0.67
     tentunya
    -0.67
     sicuramente
    -0.63
     somit
    -0.61
     Whilst
    -0.61
    POSITIVE LOGITS
    KommentareTeilen
    0.89
     propOrder
    0.85
    principalColumn
    0.84
     disambiguazione
    0.83
    GEBURTSDATUM
    0.82
    extAlignment
    0.82
    CloseOperation
    0.76
    TagMode
    0.76
    Vidite
    0.76
    脚注の使い方
    0.75
    Activations Density 0.555%

    No Known Activations