© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105861
    Prev
    Next
    INDEX
    Explanations

    references to "values" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    <bos>
    -1.20
     a
    -0.59
     an
    -0.49
     another
    -0.49
     the
    -0.47
    I
    -0.46
     A
    -0.45
    9
    -0.45
     i
    -0.45
     H
    -0.44
    POSITIVE LOGITS
     Values
    1.01
    majánló
    0.91
     values
    0.91
    Values
    0.89
     يتيمه
    0.86
    VALUES
    0.84
     ContentValues
    0.83
    values
    0.82
     VALUES
    0.80
     cherchés
    0.80
    Activations Density 0.019%

    No Known Activations