© 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. 22-GEMMASCOPE-RES-16K
    11. 14197
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Bas" and its variations, indicating a focus on a specific subject or reference in the text

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

    starting with "Bas" followed by other letters

    np_acts-logits-general · gemini-2.0-flash

    words starting with Bas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngdoc
    -0.68
     BrowserModule
    -0.67
    LookAnd
    -0.63
    rítica
    -0.62
    ImageField
    -0.60
    setViewportView
    -0.60
    withIdentifier
    -0.58
    ValueStyle
    -0.58
     chrétien
    -0.57
     ffilmiau
    -0.57
    POSITIVE LOGITS
     Bas
    0.64
    relief
    0.62
     relief
    0.57
    Bas
    0.54
     Relief
    0.53
     bas
    0.53
    #
    0.51
    ณ์
    0.49
    ษ
    0.49
    Relief
    0.49
    Activations Density 0.161%

    No Known Activations