© 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. 24-GEMMASCOPE-RES-16K
    6. 12454
    Prev
    Next
    INDEX
    Explanations

    references to reclining chairs and their features

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

    chairs or seating

    np_acts-logits-general · gemini-2.0-flash

    reclining chairs and seating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ticale
    -0.53
     Paglinawan
    -0.51
     referenties
    -0.50
    habad
    -0.50
     링크
    -0.50
    
    -0.50
     ostavi
    -0.49
    coda
    -0.49
    HomeAsUp
    -0.48
    pexpr
    -0.48
    POSITIVE LOGITS
     seat
    2.58
     seats
    2.39
     chair
    2.23
     seating
    2.16
     chairs
    2.15
     Seat
    2.10
    seat
    2.07
     Seats
    2.04
    Seat
    2.01
     seated
    1.89
    Activations Density 0.206%

    No Known Activations