© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 12660
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their properties related to health and nutrition

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

    "is" or "are" followed by a description

    np_acts-logits-general · gemini-2.0-flash

    chemical compounds present

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     berisi
    -0.57
    __((
    -0.56
     manned
    -0.53
    urethane
    -0.52
     receiving
    -0.52
    colari
    -0.52
     Receiving
    -0.52
     avanti
    -0.51
     execution
    -0.49
     Netto
    -0.49
    POSITIVE LOGITS
     present
    1.11
    present
    0.99
     présent
    0.95
    Present
    0.90
     Present
    0.90
     présents
    0.85
     PRESENT
    0.84
     presentes
    0.84
     aanwezig
    0.81
     found
    0.80
    Activations Density 1.014%

    No Known Activations