© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 12742
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "an."

    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
    findpost
    -0.98
     wireType
    -0.96
     estekak
    -0.94
     Bly
    -0.94
     Bragg
    -0.88
     radium
    -0.88
     Goldie
    -0.86
    bø
    -0.85
     Cly
    -0.84
    jsdelivr
    -0.84
    POSITIVE LOGITS
     an
    1.36
     An
    1.06
    An
    1.01
     AN
    0.93
    ran
    0.89
    an
    0.89
    cet
    0.86
    nt
    0.79
     cet
    0.78
     anex
    0.78
    Activations Density 0.227%

    No Known Activations