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. 73610
    Prev
    Next
    INDEX
    Explanations

    references to 'sm' related activities or characteristics

    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
    Voltaje
    -0.60
    NewUrlParser
    -0.59
     للمعارف
    -0.55
    GetAxis
    -0.54
     prestaciones
    -0.54
    posedge
    -0.54
    Acceso
    -0.54
    IBase
    -0.54
     bahía
    -0.53
     hendak
    -0.52
    POSITIVE LOGITS
     Sm
    1.10
     SM
    1.02
    Sm
    0.96
     sm
    0.93
    SM
    0.91
    sm
    0.84
     Smal
    0.82
     Smar
    0.75
     Smol
    0.75
     SMC
    0.74
    Activations Density 0.037%

    No Known Activations