© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6134
    Prev
    Next
    INDEX
    Explanations

    programming constructs and structures related to JSON and error responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.51
    .*")]
    -0.47
     ExecuteAsync
    -0.45
    Personendaten
    -0.45
    SharedDtor
    -0.40
    /*
    -0.38
     ModelRenderer
    -0.37
    RuleContext
    -0.36
     ویکی‌پدی
    -0.36
    msgSender
    -0.36
    POSITIVE LOGITS
    makeText
    0.65
    richTextPanel
    0.47
    '][$
    0.47
     otomatig
    0.45
    ostom
    0.44
    readystatechange
    0.42
    Autoritní
    0.42
     themſelves
    0.41
    Duel
    0.41
    randomUUID
    0.41
    Activations Density 0.255%

    No Known Activations