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. 24-GEMMASCOPE-RES-131K
    6. 932
    Prev
    Next
    INDEX
    Explanations

    sequences related to genetic material or DNA

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

    DNA sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queſta
    -0.80
     فريبيس
    -0.77
    󠁣
    -0.75
    rungsseite
    -0.73
     ddelweddau
    -0.69
    ̈́
    -0.69
    bildtitel
    -0.68
    <unused76>
    -0.66
    <unused43>
    -0.66
    <pad>
    -0.66
    POSITIVE LOGITS
    1
    0.32
     Рекоменду
    0.30
    Télécharger
    0.29
    neté
    0.28
    .”
    0.28
    5
    0.27
    seiti
    0.27
    fangen
    0.27
    Odkazy
    0.27
    repeat
    0.26
    Activations Density 0.021%

    No Known Activations