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

    Neuronpedia

    APICircuit 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. 11506
    Prev
    Next
    INDEX
    Explanations

    references to names and naming conventions

    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
     Majefty
    -0.57
     miniaturka
    -0.57
    ruitment
    -0.54
    StatusOK
    -0.52
     HttpNotFound
    -0.51
     autorytatywna
    -0.50
    quiao
    -0.49
    ModelSerializer
    -0.49
     tiguan
    -0.49
    horabuena
    -0.49
    POSITIVE LOGITS
     name
    0.85
     names
    0.81
     named
    0.72
    name
    0.69
    names
    0.65
    名字
    0.63
     NAME
    0.63
     이름
    0.61
     Names
    0.61
    NAME
    0.60
    Activations Density 0.346%

    No Known Activations