© 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. 2774
    Prev
    Next
    INDEX
    Explanations

    past tense verbs and the repetition of the word "was" in the text

    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
     côtes
    -0.83
     définiti
    -0.80
     Espinosa
    -0.79
    にあります
    -0.74
     Gerechtigkeit
    -0.73
     vœ
    -0.73
     Mommy
    -0.73
    antMatchers
    -0.72
     customization
    -0.72
    くれます
    -0.72
    POSITIVE LOGITS
     was
    1.59
     Was
    1.50
    Was
    1.50
     WAS
    1.41
    was
    1.30
     were
    1.23
     Were
    1.19
     WERE
    1.18
    Twas
    1.10
    were
    1.10
    Activations Density 0.578%

    No Known Activations