© 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. 5131
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a change in time or context, especially those starting with "now"

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

    the word "now" or temporal references indicating a moment of transition or reflection.

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

    sentence-initial transitional markers that signal a shift to a new point or emphasis.

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

    the word "Now" when it marks a transition or shift to a new topic, action, or time period.

    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
    ETIC
    -0.48
    interpolate
    -0.48
    ीय
    -0.48
    FC
    -0.45
    ulic
    -0.45
    strerror
    -0.44
    ی
    -0.43
     Fiske
    -0.42
    ge
    -0.42
     coefficient
    -0.42
    POSITIVE LOGITS
    now
    1.07
    Now
    1.06
     Now
    1.05
     NOW
    1.00
    NOW
    0.96
     now
    0.96
     Ahora
    0.90
    Jetzt
    0.87
     sekarang
    0.84
     Sekarang
    0.84
    Activations Density 0.049%

    No Known Activations