© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8536
    Prev
    Next
    INDEX
    Explanations

    instances of the word "left"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sequelize
    -0.70
    LEIA
    -0.65
     demurrer
    -0.65
     cucumbers
    -0.64
    hematical
    -0.63
    oiden
    -0.63
     Calderón
    -0.61
    éens
    -0.60
     refirió
    -0.59
     accede
    -0.59
    POSITIVE LOGITS
     left
    1.84
     Left
    1.38
     LEFT
    1.26
    Left
    1.16
    left
    1.04
    左
    0.85
    LEFT
    0.82
     laissé
    0.79
     leftover
    0.73
     laiss
    0.72
    Activations Density 0.079%

    No Known Activations