© 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. 16-GEMMASCOPE-RES-16K
    6. 6920
    Prev
    Next
    INDEX
    Explanations

    terms related to car insurance coverage options

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

    that can be abbreviated

    np_acts-logits-general · gemini-2.0-flash

    ATM card

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disponibilités
    -0.50
     времена
    -0.45
     Wallflower
    -0.45
    push
    -0.40
     држа
    -0.40
     captain
    -0.40
    de
    -0.38
    esti
    -0.38
     Captain
    -0.38
    han
    -0.38
    POSITIVE LOGITS
    WEBPACK
    0.88
     coverage
    0.86
    ThroughAttribute
    0.85
    Coverage
    0.77
     Coverage
    0.77
    unlimited
    0.75
    Manbalar
    0.74
    coverage
    0.73
    saraba
    0.72
     propOrder
    0.72
    Activations Density 0.173%

    No Known Activations