© 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. 27-GEMMASCOPE-RES-16K
    11. 10763
    Prev
    Next
    INDEX
    Explanations

    references to the word "hand" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oa̍t
    -0.55
     surla
    -0.52
     صوتيه
    -0.51
     EconPapers
    -0.48
     otomatig
    -0.47
    RTEX
    -0.47
    الحياه
    -0.47
     AppCompatTheme
    -0.45
    PyExc
    -0.44
     հղումներ
    -0.44
    POSITIVE LOGITS
     Hand
    1.17
    Hand
    1.07
     hand
    1.02
    HAND
    0.94
     HAND
    0.93
    hand
    0.90
     Hands
    0.77
     Han
    0.75
     handed
    0.73
    Han
    0.71
    Activations Density 0.117%

    No Known Activations