© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 2506
    Prev
    Next
    INDEX
    Explanations

    conjunctions and logical operators in programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ITAS
    -0.65
    numerusform
    -0.65
     zur
    -0.63
     departe
    -0.63
     Prinz
    -0.60
     keten
    -0.60
    emer
    -0.59
     verme
    -0.59
    UTS
    -0.59
    KeySpec
    -0.59
    POSITIVE LOGITS
    And
    1.41
    AND
    1.30
     And
    1.19
     Andi
    0.95
    Và
    0.92
     AND
    0.92
    and
    0.92
     Andover
    0.87
    Andi
    0.87
     Tand
    0.86
    Activations Density 0.253%

    No Known Activations