Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 67616
    Prev
    Next
    INDEX
    Explanations

    phrases related to health and safety concerns, particularly those involving risk and disease

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     pinulongan
    -0.58
    interopRequire
    -0.55
    GOTREF
    -0.52
    endregion
    -0.49
    matchCondition
    -0.47
     Wikiseite
    -0.47
     Infórmanos
    -0.47
     "..\..\
    -0.46
    #+#
    -0.45
    LookAnd
    -0.45
    POSITIVE LOGITS
     protoimpl
    0.40
     Kef
    0.39
     Савезне
    0.36
     Imágenes
    0.35
    PerPage
    0.35
     Pilipinas
    0.35
     Вікі
    0.35
     Kepler
    0.35
     eorum
    0.35
     нах
    0.34
    Activations Density 0.081%

    No Known Activations