© 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. 20-GEMMASCOPE-RES-16K
    11. 340
    Prev
    Next
    INDEX
    Explanations

    emotional responses and reactions to significant events or actions

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

    Sudden, impactful physical actions

    np_acts-logits-general · gemini-2.0-flash

    physical impact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.77
     يتيمه
    -0.66
    AndEndTag
    -0.60
     समीक्षाएं
    -0.59
    ImageContext
    -0.59
    MockBean
    -0.58
     Normdatei
    -0.57
    ViewInit
    -0.57
     utafitiHapana
    -0.57
    webElementXpaths
    -0.57
    POSITIVE LOGITS
     blow
    1.42
     blows
    1.35
     punch
    1.32
     shock
    1.31
     punches
    1.21
     hit
    1.13
     golpe
    1.11
     jolt
    1.11
    blow
    1.10
     hits
    1.10
    Activations Density 0.316%

    No Known Activations