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. 22414
    Prev
    Next
    INDEX
    Explanations

    elements that indicate the presence of scientific data or technical specifications

    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
    蚪
    -0.46
     ModelExpression
    -0.41
    tangentMode
    -0.34
    Totale
    -0.32
     familières
    -0.31
    mbic
    -0.31
    SeekBar
    -0.29
    graphicx
    -0.29
    UnknownFieldSet
    -0.29
    shortcuts
    -0.28
    POSITIVE LOGITS
     autorytatywna
    0.82
     виправивши
    0.64
    الدراسه
    0.62
     disambiguazione
    0.62
    RTLD
    0.55
    WriteBarrier
    0.54
     indisponible
    0.54
    #+#
    0.50
     Autorizaciones
    0.50
     '\\;'
    0.50
    Activations Density 0.009%

    No Known Activations