© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 7617
    Prev
    Next
    INDEX
    Explanations

    expressions of doubt or contradiction, especially in the context of relationships and values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Almost
    -0.50
     Almost
    -0.49
    almost
    -0.48
     <<<<<<<<<<<<<<
    -0.46
    ThroughAttribute
    -0.46
     almost
    -0.45
     persino
    -0.45
    Either
    -0.43
     quase
    -0.42
    LookAnd
    -0.42
    POSITIVE LOGITS
     necessarily
    1.66
    necessarily
    1.32
     necessariamente
    1.30
     necesariamente
    1.24
     nécessairement
    1.07
     always
    1.07
     Necess
    1.01
     nødvendig
    0.96
     automatically
    0.93
    always
    0.93
    Activations Density 0.815%

    No Known Activations