© 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. 11996
    Prev
    Next
    INDEX
    Explanations

    questions and statements about problems and realities

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

    Follows a question/problem/reality/truth

    np_acts-logits-general · gemini-2.0-flash

    question and problem framing

    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
    
    -0.88
     المعيارى
    -0.75
    addCriterion
    -0.74
     leaſt
    -0.70
    ]--;
    -0.68
    SequentialGroup
    -0.67
     صوتيه
    -0.66
    +#+#
    -0.66
    extAlignment
    -0.65
     EconPapers
    -0.65
    POSITIVE LOGITS
     is
    0.90
     then
    0.72
     here
    0.67
     hierv
    0.65
     today
    0.55
     entonces
    0.54
     therefore
    0.54
     isn
    0.53
     remains
    0.53
     may
    0.52
    Activations Density 0.258%

    No Known Activations