© 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. 8444
    Prev
    Next
    INDEX
    Explanations

    terms related to decision-making and problem-solving contexts

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

    problem solving or decision making

    np_acts-logits-general · gemini-2.0-flash

    solution-oriented decision making

    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
    PerformLayout
    -0.80
     fubject
    -0.79
    IntoConstraints
    -0.76
     reaſon
    -0.74
    ſelf
    -0.72
     poffible
    -0.72
     beſt
    -0.71
    ſelves
    -0.69
    endphp
    -0.69
     Перейти
    -0.68
    POSITIVE LOGITS
     oriented
    0.57
    -
    0.52
    focused
    0.50
     محور
    0.49
     driven
    0.48
    oriented
    0.48
     nahilalakip
    0.47
     creation
    0.47
    @[+][
    0.47
    generating
    0.46
    Activations Density 0.469%

    No Known Activations