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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 68832
    Prev
    Next
    INDEX
    Explanations

    phrases related to safety protocols and social distance measures

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

    end of turn

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     yö
    -0.37
     CreateTagHelper
    -0.32
     détaillés
    -0.32
     旗
    -0.31
     cela
    -0.31
     aislamiento
    -0.31
     öne
    -0.30
     olmak
    -0.30
    éndole
    -0.30
     közül
    -0.29
    POSITIVE LOGITS
    WillAppear
    0.68
    دانشنامهٔ
    0.57
    featureID
    0.54
    onOptions
    0.53
     resourceCulture
    0.52
     Exacts
    0.51
    Хьажоргаш
    0.50
    hyrchwyd
    0.50
     Monfieur
    0.49
    تفصیلات
    0.49
    Activations Density 0.003%

    No Known Activations