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. 53758
    Prev
    Next
    INDEX
    Explanations

    repeating patterns or sequences in data related to molecular or chemical structures

    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
    principalColumn
    -0.63
     AssemblyVersion
    -0.49
     ब्रेकडाउन
    -0.48
    RTCK
    -0.47
    MessageTagHelper
    -0.45
     DBNull
    -0.45
     pinulongan
    -0.43
    DIPSETTING
    -0.41
     reducer
    -0.40
    cairo
    -0.40
    POSITIVE LOGITS
    .*")]
    0.59
    :✨
    0.55
     مؤرشف
    0.49
    ----</
    0.48
    حياته
    0.47
    躇
    0.46
    tagHelperRunner
    0.46
    ๆ
    0.45
     שוליים
    0.45
    Mereka
    0.45
    Activations Density 0.046%

    No Known Activations