© 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. 5991
    Prev
    Next
    INDEX
    Explanations

    references to the name "Ku" or variations of it

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

    Tokens followed by "hlmann" or "uc"

    np_acts-logits-general · gemini-2.0-flash

    Kuhlmann or Ku followed by Li

    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
    moveToFirst
    -0.58
    ContentAsync
    -0.53
     cam
    -0.51
     дописавши
    -0.49
     further
    -0.47
     przys
    -0.47
     aufges
    -0.47
     Cam
    -0.46
     wave
    -0.45
    AndEndTag
    -0.45
    POSITIVE LOGITS
     سكانية
    0.73
     >=",
    0.71
     Kombat
    0.70
    Jeografia
    0.67
    étés
    0.64
     textStatus
    0.64
    lusconi
    0.64
    הערות
    0.63
     Igles
    0.63
    Біографія
    0.62
    Activations Density 0.080%

    No Known Activations