© 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. 6475
    Prev
    Next
    INDEX
    Explanations

    references to writers and writing roles

    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
    catraz
    -0.72
     Bourgoin
    -0.71
    ochial
    -0.70
     Pless
    -0.68
    üß
    -0.67
     sabbia
    -0.66
    polate
    -0.63
    racuse
    -0.63
    foss
    -0.63
    precip
    -0.62
    POSITIVE LOGITS
     writer
    2.36
    writer
    2.15
     Writer
    2.13
     writers
    2.09
     Writers
    1.93
    Writer
    1.87
     WRITER
    1.84
    Writers
    1.82
    writers
    1.74
    WRITER
    1.53
    Activations Density 0.060%

    No Known Activations