© 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. 20-GEMMASCOPE-RES-16K
    6. 10648
    Prev
    Next
    INDEX
    Explanations

    phrases indicating recommendations or advice

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

    "Let's" or "Let" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    "let's" followed by a verb

    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
    WireFormatLite
    -0.73
    InjectAttribute
    -0.70
     <<<<<<<<<<<<<<
    -0.68
    makeConstraints
    -0.66
     >=",
    -0.65
     pinulongan
    -0.64
    ustomed
    -0.60
    Résultats
    -0.60
    ondissement
    -0.60
     mourut
    -0.59
    POSITIVE LOGITS
     lets
    1.02
    Lets
    0.97
     Lets
    0.94
     let
    0.86
     say
    0.78
     see
    0.72
     assume
    0.72
     face
    0.70
    lets
    0.69
     Let
    0.69
    Activations Density 0.041%

    No Known Activations