© 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. 6883
    Prev
    Next
    INDEX
    Explanations

    details related to room features and amenities

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

    Follows nouns related to manufacturing or components

    np_acts-logits-general · gemini-2.0-flash

    parts and possibilities

    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
     Theſe
    -1.19
     itſelf
    -1.08
     Monfieur
    -1.08
     Anſ
    -1.06
     Houſe
    -1.05
    WebVitals
    -1.03
     myſelf
    -1.01
    ITERATURE
    -1.01
     Efq
    -1.00
    enumi
    -0.99
    POSITIVE LOGITS
     /
    0.68
    <eos>
    0.61
     suitable
    0.61
     Ø
    0.57
     +
    0.56
     
    0.55
    Possibility
    0.55
     possibility
    0.54
    ↵
    0.52
    又は
    0.51
    Activations Density 0.304%

    No Known Activations