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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 1991
    Prev
    Next
    INDEX
    Explanations

    references to checking or verification processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gilmour
    -0.74
    APN
    -0.67
    /−
    -0.66
    vocations
    -0.66
    ließen
    -0.66
     Jahr
    -0.64
    setContentType
    -0.62
    subpackage
    -0.62
    醐
    -0.61
    splitlines
    -0.61
    POSITIVE LOGITS
     CHECK
    2.06
    CHECK
    1.85
     checks
    1.83
     Checks
    1.82
     Check
    1.80
    check
    1.73
     check
    1.73
     Checking
    1.71
    Check
    1.70
     checkers
    1.69
    Activations Density 0.041%

    No Known Activations