© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 5752
    Prev
    Next
    INDEX
    Explanations

    instances of confirmation or verification of statements or findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sk
    -0.71
     Rok
    -0.68
    Rok
    -0.66
    z
    -0.63
     Ling
    -0.60
    Sk
    -0.60
    േ
    -0.57
    duction
    -0.57
    jsx
    -0.56
     she
    -0.56
    POSITIVE LOGITS
     Confirm
    2.04
     confirmations
    2.02
     confirmed
    1.98
     confirmation
    1.95
     confirm
    1.95
     Confirmed
    1.93
     confirms
    1.92
     Confirmation
    1.89
     confirming
    1.83
    confirmed
    1.82
    Activations Density 0.148%

    No Known Activations