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
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 742
    Prev
    Next
    INDEX
    Explanations

    structured data representations and delimiters

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

    latex syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snippetHide
    -1.03
    parsedMessage
    -1.00
    RegressionTest
    -0.91
    Personensuche
    -0.88
    +#+#
    -0.87
     Италијани
    -0.87
     disambiguazione
    -0.86
    PerformLayout
    -0.83
    httphttps
    -0.79
     Signalez
    -0.79
    POSITIVE LOGITS
     visualización
    0.43
    .
    0.41
     economía
    0.35
     Gillespie
    0.35
     transición
    0.33
    '
    0.33
     combinación
    0.33
     caída
    0.31
     própria
    0.31
    !
    0.31
    Activations Density 0.006%

    No Known Activations