© 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. 7386
    Prev
    Next
    INDEX
    Explanations

    code-related terms and API functions in a programming context

    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
    Preventing
    -0.72
     Preventing
    -0.64
     CreateTagHelper
    -0.57
     preventing
    -0.56
    Prevention
    -0.56
    Controlling
    -0.55
     stabilizing
    -0.54
     Prevention
    -0.52
     Controlling
    -0.52
    awtextra
    -0.51
    POSITIVE LOGITS
    protected
    1.00
     protected
    0.99
     prote
    0.90
     Protected
    0.72
    Protected
    0.71
     Prote
    0.71
     protegido
    0.69
     bảo
    0.68
     protegida
    0.67
     PROTECT
    0.66
    Activations Density 0.410%

    No Known Activations