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. 12541
    Prev
    Next
    INDEX
    Explanations

    language and cultural identifiers related to different nationalities

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

    adjectival references to nationalities, languages, or countries (demonyms/ethnonyms).

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab
    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
    rungsseite
    -0.64
    ValueStyle
    -0.56
    曖昧さ回避
    -0.54
     typelib
    -0.54
     onAnimation
    -0.51
    protoimpl
    -0.49
    poptosis
    -0.48
    featureID
    -0.48
    ddots
    -0.46
    tonode
    -0.45
    POSITIVE LOGITS
    Chinese
    0.81
    Russian
    0.81
    Japanese
    0.80
    Spanish
    0.80
    German
    0.80
     Spanish
    0.79
     German
    0.79
     Russian
    0.78
     Indian
    0.78
    French
    0.78
    Activations Density 0.295%

    No Known Activations