© 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 - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 647
    Prev
    Next
    INDEX
    Explanations

    email-related information, including addresses and contact requests

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

    names and early occurrences

    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
     CURIAM
    -0.57
    ragalactic
    -0.54
    onViewCreated
    -0.53
    GeoNames
    -0.53
    IntoConstraints
    -0.52
    دانشنامهٔ
    -0.52
    ftagPool
    -0.50
     Esatti
    -0.50
    didSet
    -0.50
    reszcie
    -0.49
    POSITIVE LOGITS
     Earn
    0.36
     NB
    0.34
    }`).
    0.33
     disambiguazione
    0.32
     GAT
    0.32
    ↩
    0.31
    uesia
    0.31
     связа
    0.31
     CSM
    0.31
     Pran
    0.30
    Activations Density 0.004%

    No Known Activations