© 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. 18-GEMMASCOPE-RES-16K
    6. 9754
    Prev
    Next
    INDEX
    Explanations

    numerical values or statistics

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

    Numbers within identifiers or URLs

    np_acts-logits-general · gemini-2.0-flash

    old English spellings like itſelf

    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
    ese
    -0.60
    BagLayout
    -0.58
    Controllo
    -0.58
    LIOT
    -0.57
     pl
    -0.56
    mello
    -0.55
    TI
    -0.55
    LayoutPanel
    -0.54
    ge
    -0.54
     numberWith
    -0.54
    POSITIVE LOGITS
    AndEndTag
    0.89
    0
    0.77
    AddTagHelper
    0.72
     tfsi
    0.72
     alfalfa
    0.72
     poffible
    0.71
     myſelf
    0.69
     itſelf
    0.69
     fubject
    0.69
     crdi
    0.69
    Activations Density 0.215%

    No Known Activations