© 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. 8454
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings and judicial contexts

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

    followed by verbs like "assert" or "is"

    np_acts-logits-general · gemini-2.0-flash

    people, states, defendants, Ramblers, GNU licences

    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
    -0.87
     ujednoznacz
    -0.79
     esetén
    -0.68
    RectangleBorder
    -0.66
     @"/
    -0.64
     виправивши
    -0.64
     transfieras
    -0.63
     &___
    -0.62
    NameInMap
    -0.60
     дописавши
    -0.58
    POSITIVE LOGITS
    CheckedChanged
    0.58
    typeorm
    0.53
    탤
    0.52
    reactstrap
    0.52
    saurus
    0.51
    angkutan
    0.49
     useDispatch
    0.48
    $​
    0.48
    zeitige
    0.48
    фии
    0.48
    Activations Density 1.158%

    No Known Activations