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. 5977
    Prev
    Next
    INDEX
    Explanations

    references to subjects or topics of discussion

    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
     مشين
    -0.60
    InjectAttribute
    -0.58
    autop
    -0.54
    WaitGroup
    -0.53
    EFIAPI
    -0.53
     pinulongan
    -0.53
    Билгалдахарш
    -0.53
    ⓘ
    -0.53
    MCS
    -0.52
     прока
    -0.52
    POSITIVE LOGITS
     matter
    0.75
    Subjects
    0.74
     topic
    0.68
     äm
    0.67
     Matter
    0.66
     MATTER
    0.66
    Subject
    0.65
     subject
    0.65
     Subject
    0.64
     Topic
    0.64
    Activations Density 0.335%

    No Known Activations