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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 68918
    Prev
    Next
    INDEX
    Explanations

    references to statistics about births, deaths, and living individuals in various categories

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

    living people

    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
     برانيه
    -0.55
     utafitiHapana
    -0.47
     resourceCulture
    -0.47
    )}_
    -0.45
    AndEndTag
    -0.43
    InSection
    -0.42
    gasse
    -0.41
    )}_{
    -0.41
     ModelExpression
    -0.40
    TagNumber
    -0.40
    POSITIVE LOGITS
     الحره
    0.96
     autorità
    0.79
    Kontrola
    0.60
    Portail
    0.57
     المعيارى
    0.55
     virtuel
    0.53
    GEBURTSDATUM
    0.49
    OGND
    0.47
    Hentet
    0.46
     OFDb
    0.43
    Activations Density 0.019%

    No Known Activations