© 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. 9000
    Prev
    Next
    INDEX
    Explanations

    quantifiable numerical values and their corresponding significance in context

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

    Numbers with decimals

    np_acts-logits-general · gemini-2.0-flash

    numbers and units (%) cm

    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
     @"/
    -0.88
    featureID
    -0.77
    AddTagHelper
    -0.75
     صوتيه
    -0.73
    belea
    -0.69
     ویکی‌پدی
    -0.65
     للاسماء
    -0.64
    цезда
    -0.64
     yyl
    -0.63
    AdapterFactory
    -0.62
    POSITIVE LOGITS
    Lähteet
    0.60
    Hozzáférés
    0.60
     embargo
    0.57
    版本
    0.54
    xlarge
    0.54
     entanto
    0.53
    Rptr
    0.53
    midler
    0.53
     Exactos
    0.52
    msford
    0.52
    Activations Density 0.874%

    No Known Activations