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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 51711
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and transformations associated with statistical analysis

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     nakalista
    -0.93
    GEBURTSDATUM
    -0.84
    Personensuche
    -0.79
    rungsseite
    -0.73
     ब्रेकडाउन
    -0.68
    +#+#
    -0.66
    出版年
    -0.65
    IsContent
    -0.65
    MemoryWarning
    -0.64
    KommentareTeilen
    -0.63
    POSITIVE LOGITS
    czes
    0.33
    好
    0.32
     Rot
    0.32
    ẵ
    0.31
    CodedInputStream
    0.30
    Rot
    0.30
    Do
    0.30
    новништво
    0.29
    Channel
    0.28
    ARROLL
    0.28
    Activations Density 0.161%

    No Known Activations