© 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. 18-GEMMASCOPE-RES-16K
    6. 3453
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the passage of time or transitions in narratives

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

    "Now" as an introductory word

    np_acts-logits-general · gemini-2.0-flash

    "Now" to start a new point

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    клопе
    -0.75
    AndEndTag
    -0.74
    xase
    -0.69
     ExecuteAsync
    -0.68
    сторія
    -0.68
     Efq
    -0.67
    WriteBarrier
    -0.67
    GIVEREF
    -0.67
    AsUp
    -0.66
     propOrder
    -0.65
    POSITIVE LOGITS
     imagine
    0.75
     why
    0.70
     NOW
    0.68
     Now
    0.67
    Now
    0.63
     now
    0.62
     how
    0.58
     admittedly
    0.57
    NOW
    0.55
    totalSupply
    0.55
    Activations Density 0.030%

    No Known Activations