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. 131024
    Prev
    Next
    INDEX
    Explanations

    graphical representations and structures in data, indicating visual organization or patterns

    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
     Inscrivez
    -0.43
    itinéraire
    -0.39
    zusetzen
    -0.36
     prestaciones
    -0.35
    什么呢
    -0.35
     Acceso
    -0.33
    sprogramm
    -0.33
    toDate
    -0.33
    处于
    -0.32
     triko
    -0.32
    POSITIVE LOGITS
     كومونز
    0.63
    OGND
    0.60
     يتيمه
    0.58
    SequentialGroup
    0.56
    scriptcase
    0.55
     Paglinawan
    0.54
    RTLI
    0.54
    UnusedPrivate
    0.54
    marvin
    0.52
    WithIOException
    0.51
    Activations Density 0.292%

    No Known Activations