© 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. 12-GEMMASCOPE-RES-16K
    6. 11407
    Prev
    Next
    INDEX
    Explanations

    commands and phrases related to verification or validation actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    APN
    -0.68
    /−
    -0.65
    醐
    -0.64
     Gilmour
    -0.63
    FECT
    -0.60
    ğraf
    -0.58
    subpackage
    -0.58
    >>>>>>>>
    -0.57
    Slices
    -0.57
    ERe
    -0.57
    POSITIVE LOGITS
     CHECK
    1.64
     checkers
    1.49
    CHECK
    1.47
     Checks
    1.44
     checks
    1.39
     Checking
    1.36
     Check
    1.32
    checks
    1.32
     Checked
    1.29
     checked
    1.28
    Activations Density 0.052%

    No Known Activations