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. 130998
    Prev
    Next
    INDEX
    Explanations

    instances of the token 'x' followed by various numbers and characters

    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
     autorytatywna
    -0.65
    ⓧ
    -0.64
     Administrativna
    -0.58
    Autoritní
    -0.47
     disambiguazione
    -0.47
    tagHelperRunner
    -0.46
     kasarigan
    -0.45
    LEGGI
    -0.43
    adaptiveStyles
    -0.42
     Japón
    -0.41
    POSITIVE LOGITS
    BeginInit
    0.63
    EndInit
    0.58
     neutral
    0.49
     مشين
    0.48
    <bos>
    0.48
     ELE
    0.48
     neutr
    0.48
     neutrals
    0.47
    WriteLiteral
    0.45
     Neutr
    0.43
    Activations Density 0.186%

    No Known Activations