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. 122995
    Prev
    Next
    INDEX
    Explanations

    specific numerical values and punctuation in the text

    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
     utafitiHapana
    -0.79
    oredCriteria
    -0.76
    httphttps
    -0.73
     wireType
    -0.73
     חיצוניים
    -0.73
     OMITBAD
    -0.70
     فريبيس
    -0.70
     defaultstate
    -0.70
     iconLine
    -0.68
     EconPapers
    -0.68
    POSITIVE LOGITS
     prefi
    0.31
     confé
    0.29
     yearly
    0.28
    ↵↵
    0.28
    __":
    0.28
     notes
    0.28
    DIPSETTING
    0.27
    看
    0.27
     numbers
    0.26
    ocities
    0.26
    Activations Density 0.050%

    No Known Activations