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. 20-GEMMASCOPE-RES-131K
    6. 16369
    Prev
    Next
    INDEX
    Explanations

    references to specific sections and numbers in a document

    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
    OCCURRED
    -0.46
    verwijspagina
    -0.46
    <?
    -0.41
    //
    -0.40
     feudal
    -0.39
    apunov
    -0.39
     cons
    -0.38
    setLogin
    -0.36
    UIView
    -0.36
     bondage
    -0.36
    POSITIVE LOGITS
    +#+#
    0.60
     idéia
    0.51
    tehende
    0.46
    AddRange
    0.46
     informée
    0.46
    EditorBrowsable
    0.44
    SuspendLayout
    0.43
    oredCriteria
    0.42
    ibouti
    0.41
    PerformLayout
    0.41
    Activations Density 0.040%

    No Known Activations