© 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. 7858
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and operations involving sets and ideals

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

    Mathematical or logical notation/symbols

    np_acts-logits-general · gemini-2.0-flash

    Stella D'oro union

    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
     McConnell
    -0.83
    Guil
    -0.76
     Pohl
    -0.72
     Guil
    -0.72
     Cheshire
    -0.69
     Oke
    -0.66
     Greta
    -0.64
     Merritt
    -0.63
     SOT
    -0.62
     Amelia
    -0.62
    POSITIVE LOGITS
     Corbett
    0.71
     Norwood
    0.71
     Shand
    0.63
     LTD
    0.61
     Boyce
    0.60
     acetic
    0.60
     Bundy
    0.60
     Hyman
    0.60
     Ferguson
    0.59
     Holliday
    0.58
    Activations Density 1.478%

    No Known Activations