© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2451
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical events and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    past tense verbs involving actions or events (particularly those using "had" and "been").

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    past perfect constructions, especially “had” + past participle and passive “had been …” structures.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the past perfect verb phrase "had been" in formal or legal texts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kicks
    -0.46
     goes
    -0.44
     sienta
    -0.43
     pops
    -0.39
     فريبيس
    -0.38
     faisons
    -0.38
    goes
    -0.38
     gets
    -0.37
     noDo
    -0.36
     breaks
    -0.36
    POSITIVE LOGITS
     previously
    0.77
     had
    0.73
     zuvor
    0.69
    previously
    0.68
     previamente
    0.66
     anteriormente
    0.64
     hatte
    0.63
     originally
    0.63
     earlier
    0.63
     había
    0.62
    Activations Density 0.259%

    No Known Activations