© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 8922
    Prev
    Next
    INDEX
    Explanations

    references to social or economic structures and their classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paglinawan
    -0.57
    Tembelea
    -0.50
     CreateTagHelper
    -0.50
    ardia
    -0.46
    adan
    -0.45
    aside
    -0.44
     Charming
    -0.44
    Rhestr
    -0.43
     ModelRenderer
    -0.43
    mazing
    -0.42
    POSITIVE LOGITS
    EDEFAULT
    0.47
    rungsseite
    0.45
     الحره
    0.41
    webElementGuid
    0.40
     ones
    0.37
     بيها
    0.37
    SequentialGroup
    0.35
    gebnisse
    0.34
    Activités
    0.34
     samarbeid
    0.34
    Activations Density 1.157%

    No Known Activations