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. 20-GEMMASCOPE-RES-16K
    6. 137
    Prev
    Next
    INDEX
    Explanations

    connections to food and cuisine-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the phrase "Speaking of", which seems to be used as a transition or topic-shifting device in writing.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     パンチラ
    -0.88
    ſſung
    -0.86
    
    -0.86
     Menſchen
    -0.85
    <unused43>
    -0.85
    bildtitel
    -0.85
    <unused8>
    -0.84
    [@BOS@]
    -0.84
    <unused42>
    -0.84
    <unused68>
    -0.84
    POSITIVE LOGITS
    <eos>
    0.29
     memang
    0.29
    ,
    0.23
     vốn
    0.23
    mittags
    0.23
     also
    0.22
     niej
    0.22
     (
    0.22
     infatti
    0.22
    static
    0.21
    Activations Density 0.195%

    No Known Activations