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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 11260
    Prev
    Next
    INDEX
    Explanations

    references to mobile applications and related technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.74
     كومونز
    -0.55
    IntoConstraints
    -0.49
    expandindo
    -0.47
     propOrder
    -0.44
     CreateTagHelper
    -0.38
     CURLOPT
    -0.38
    GOTREF
    -0.37
    CloseOperation
    -0.35
    ">//
    -0.35
    POSITIVE LOGITS
     app
    2.11
     apps
    1.64
     App
    1.58
    app
    1.52
     APP
    1.48
    アプリ
    1.47
    App
    1.38
     aplicativo
    1.36
     приложение
    1.34
    APP
    1.30
    Activations Density 0.371%

    No Known Activations