© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 10747
    Prev
    Next
    INDEX
    Explanations

    important phrases and key concepts related to challenges or issues in various contexts

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

    Follows "a" or "the" and precedes a noun

    np_acts-logits-general · gemini-2.0-flash

    major or important characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    J
    -0.44
    不愧
    -0.43
    ActionEvent
    -0.42
    It
    -0.41
    ese
    -0.41
    HideFlags
    -0.39
    TM
    -0.39
     craftsmanship
    -0.39
    Great
    -0.38
    esehen
    -0.38
    POSITIVE LOGITS
    новништво
    0.85
    InputBorder
    0.82
     dụ
    0.74
     key
    0.71
     focus
    0.70
    енча
    0.70
    ContentAlignment
    0.70
     clés
    0.69
    Vidite
    0.69
    ⓧ
    0.67
    Activations Density 0.308%

    No Known Activations