© 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. 11395
    Prev
    Next
    INDEX
    Explanations

    phrases related to capabilities or abilities, particularly in the context of actions that cannot be performed

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

    Japanese sentence ending phrases

    np_acts-logits-general · gemini-2.0-flash

    sentence endings

    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
    ArrowToggle
    -0.72
    expandindo
    -0.71
     Waray
    -0.70
    kloped
    -0.68
    WithIOException
    -0.63
     CMM
    -0.61
     _)
    -0.60
     kaarangay
    -0.60
    bly
    -0.57
    Rujuakan
    -0.57
    POSITIVE LOGITS
    .
    0.56
    WHEREAS
    0.46
     bezeichnen
    0.46
    DoubleQuotes
    0.46
     iconLine
    0.45
     veckan
    0.44
    MUST
    0.43
    MathML
    0.43
    وبه
    0.42
    ypress
    0.41
    Activations Density 0.027%

    No Known Activations