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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5974
    Prev
    Next
    INDEX
    Explanations

    terms related to precision and exactness in definitions or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.70
     esternos
    -0.65
    adaptiveStyles
    -0.62
    ilever
    -0.60
     informée
    -0.59
     koszulka
    -0.59
     indígen
    -0.58
    Manbalar
    -0.57
    pompa
    -0.57
     bershka
    -0.57
    POSITIVE LOGITS
    precise
    0.95
     precisely
    0.91
     precise
    0.88
     exact
    0.87
     EXACT
    0.86
     Precise
    0.85
    exact
    0.84
     exac
    0.83
    Precise
    0.83
     exactly
    0.81
    Activations Density 0.273%

    No Known Activations