© 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. 15714
    Prev
    Next
    INDEX
    Explanations

    connections and findings related to studies on metabolism and immune responses

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

    like "shed," "illuminate," or "reveal"

    np_acts-logits-general · gemini-2.0-flash

    shed light on or reveal information

    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
    setVerticalGroup
    -0.51
     kies
    -0.51
    works
    -0.49
     Numerade
    -0.49
    worked
    -0.48
     worked
    -0.48
    recated
    -0.48
    Automatically
    -0.47
    patron
    -0.47
     Sosten
    -0.46
    POSITIVE LOGITS
     shed
    1.37
    shed
    1.28
     sheds
    1.25
     shedding
    1.15
     Shed
    1.00
     illuminate
    0.97
     illuminates
    0.96
     illuminating
    0.93
    illumin
    0.89
     revealing
    0.89
    Activations Density 0.606%

    No Known Activations