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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15944
    Prev
    Next
    INDEX
    Explanations

    references to digital citizenship and the responsible use of technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    hyrchwyd
    -0.74
    adaptiveStyles
    -0.67
    GraphicsUnit
    -0.67
     ब्रेकडाउन
    -0.63
    TypedDataSet
    -0.62
     '\\;'
    -0.61
    expandindo
    -0.61
    دانشنامهٔ
    -0.61
    writeFieldEnd
    -0.60
    uttavia
    -0.59
    POSITIVE LOGITS
    WSGI
    0.39
     ſou
    0.32
     ayer
    0.31
     Numerade
    0.30
    Lähteet
    0.30
     artesan
    0.29
    ğiniz
    0.29
     period
    0.28
     etme
    0.28
    HasColumnType
    0.27
    Activations Density 0.865%

    No Known Activations