© 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. 13150
    Prev
    Next
    INDEX
    Explanations

    layers and materials used in electronic device construction

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

    "Photo" or related to light emission

    np_acts-logits-general · gemini-2.0-flash

    photoluminescence

    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
     onCancelled
    -0.76
    tighets
    -0.58
    ftagPool
    -0.58
    SuppressMessage
    -0.57
    Diweddarwch
    -0.55
    ölkerung
    -0.55
     المعيارى
    -0.55
     sanitario
    -0.54
    IBOutlet
    -0.54
    دانشنامهٔ
    -0.54
    POSITIVE LOGITS
     photo
    0.65
     Photo
    0.58
    Photo
    0.56
    PreferredItem
    0.56
    :✨
    0.55
    abestanden
    0.55
     π
    0.55
    LUM
    0.54
    photo
    0.52
     foto
    0.51
    Activations Density 0.878%

    No Known Activations