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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 5135
    Prev
    Next
    INDEX
    Explanations

    references to legal actions and testimonies in reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.34
     TabLayout
    -0.33
    featureID
    -0.31
     gap
    -0.31
     fast
    -0.31
    CDCl
    -0.29
    (=)
    -0.29
     fun
    -0.29
     NOI
    -0.28
     many
    -0.28
    POSITIVE LOGITS
     Efq
    0.79
    KommentareTeilen
    0.76
     himſelf
    0.72
     queſta
    0.71
    ſelben
    0.69
    ſcher
    0.69
    opsida
    0.68
    himself
    0.67
    ésultats
    0.66
     dieſe
    0.65
    Activations Density 0.853%

    No Known Activations