Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7944
    Prev
    Next
    INDEX
    Explanations

    terminology related to legal proceedings and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.80
    invokeLater
    -0.72
    webElementXpaths
    -0.70
     otomatig
    -0.68
    adaptiveStyles
    -0.68
    gonic
    -0.66
    ReusableCell
    -0.66
    localctx
    -0.66
    Jîn
    -0.65
    tonode
    -0.65
    POSITIVE LOGITS
     consult
    0.52
     consultation
    0.51
     consultations
    0.49
     Consultation
    0.42
     consulted
    0.42
     Consult
    0.42
    consultation
    0.40
     CONSULT
    0.40
    consult
    0.39
     consulta
    0.39
    Activations Density 0.721%

    No Known Activations