© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 6105
    Prev
    Next
    INDEX
    Explanations

    instances of the word "full" in various contexts

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

    "full"

    np_acts-logits-general · gemini-2.0-flash

    full followed by specifying nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    گاب
    -0.36
    šanu
    -0.35
     ligiloj
    -0.35
     '{@
    -0.34
     j
    -0.34
    Étape
    -0.34
     Warne
    -0.34
    ia
    -0.33
    eth
    -0.33
    gesetz
    -0.33
    POSITIVE LOGITS
     Full
    1.19
     full
    1.08
    Full
    1.06
     FULL
    1.05
    FULL
    0.96
    full
    0.91
    フル
    0.83
     полно
    0.82
    isFull
    0.81
     fuller
    0.79
    Activations Density 0.102%

    No Known Activations