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. 1015
    Prev
    Next
    INDEX
    Explanations

    topics related to health conditions and treatments

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

    diseases, safety, effects, processes

    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
    iſchen
    -0.66
    ViewImports
    -0.65
     CanadaChoose
    -0.63
    𖤍
    -0.59
    iſche
    -0.59
    pecabe
    -0.58
    ⭏
    -0.58
    elashes
    -0.58
    oa̍t
    -0.58
    protoimpl
    -0.58
    POSITIVE LOGITS
     مشين
    0.37
     including
    0.29
    Diweddarwch
    0.28
    ParallelGroup
    0.27
    expandindo
    0.26
     via
    0.24
     Ressource
    0.23
     Including
    0.23
    叶凌天
    0.21
    ceğine
    0.20
    Activations Density 0.102%

    No Known Activations