© 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. 8234
    Prev
    Next
    INDEX
    Explanations

    keywords related to web requests and APIs, specifically focusing on operations like reading, creating, updating, and deleting resources within a client-server architecture

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

    Follows specific function names (List, Get, Group)

    np_acts-logits-general · gemini-2.0-flash

    API request preparation

    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
    GEBURTSDATUM
    -0.83
    rungsseite
    -0.79
    AndEndTag
    -0.78
    enterOuterAlt
    -0.77
    WireFormatLite
    -0.73
    ReusableCell
    -0.66
     Roskov
    -0.65
    SharedDtor
    -0.63
     gainera
    -0.63
    featureID
    -0.63
    POSITIVE LOGITS
     tfsi
    0.62
     !”
    0.61
     ?"
    0.59
    BagConstraints
    0.57
     تضيفلها
    0.57
     ?”
    0.56
    ]}"
    0.56
     !"
    0.54
     !'
    0.54
     hentai
    0.54
    Activations Density 0.104%

    No Known Activations