© 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. 38-GEMMASCOPE-RES-16K
    6. 9114
    Prev
    Next
    INDEX
    Explanations

    references to legal terminology and procedural descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paglinawan
    -0.55
    alien
    -0.55
     propOrder
    -0.55
     GenerationType
    -0.53
    alias
    -0.52
    ⓧ
    -0.49
    MessageTagHelper
    -0.49
    TagMode
    -0.48
    علی
    -0.47
    InjectAttribute
    -0.47
    POSITIVE LOGITS
     Al
    3.44
    Al
    3.05
     al
    2.58
    アル
    1.75
     AL
    1.64
     Аль
    1.59
     アル
    1.53
     Ал
    1.49
    al
    1.38
     аль
    1.34
    Activations Density 0.951%

    No Known Activations