© 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. 4-GEMMASCOPE-RES-16K
    11. 10782
    Prev
    Next
    INDEX
    Explanations

    instances of the word "written" and its derivatives in various contexts

    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
    ganggu
    -0.87
    vericks
    -0.77
     تانيه
    -0.77
    sampler
    -0.75
    requireNonNull
    -0.72
     ModelExpression
    -0.72
    tvguidetime
    -0.72
    minyak
    -0.71
    Reprodução
    -0.70
     reliefs
    -0.70
    POSITIVE LOGITS
     written
    1.85
     Written
    1.68
    Written
    1.66
    written
    1.58
     WRITTEN
    1.38
     spoken
    1.04
     escrito
    0.96
     printed
    0.94
     écrite
    0.87
     escrita
    0.79
    Activations Density 0.183%

    No Known Activations