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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104789
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate inclusion or specification of items or examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     betweenstory
    -0.46
    msgSender
    -0.41
    toThrow
    -0.38
    initComponents
    -0.37
     raiſ
    -0.36
     ferait
    -0.36
    Reprodução
    -0.36
     feroit
    -0.36
    PostInfinity
    -0.35
    GEBURTSDATUM
    -0.35
    POSITIVE LOGITS
     Types
    0.55
     types
    0.55
     non
    0.51
     kinds
    0.51
     subtypes
    0.50
     classic
    0.50
     Rolf
    0.50
     odious
    0.50
    ypes
    0.50
     fieldNum
    0.50
    Activations Density 0.086%

    No Known Activations