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. 6424
    Prev
    Next
    INDEX
    Explanations

    references to various types of artifacts 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 @ 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
     yoghurt
    -0.75
    KommentareTeilen
    -0.75
    MockBean
    -0.73
     aeroplane
    -0.70
     enquiry
    -0.70
     fertiliser
    -0.68
     beetroot
    -0.67
    parsedMessage
    -0.67
    Programme
    -0.66
    TargetException
    -0.66
    POSITIVE LOGITS
     Prancis
    0.64
     Larson
    0.63
    ency
    0.58
    اً
    0.58
     Theater
    0.57
     Harbor
    0.57
     Peterson
    0.57
     Pacífico
    0.57
    Canceled
    0.56
     confiable
    0.56
    Activations Density 1.678%

    No Known Activations