© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 13289
    Prev
    Next
    INDEX
    Explanations

    code-related terminologies or programming constructs within the text

    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
    将她
    -0.45
     ◄
    -0.41
    之时
    -0.40
     cease
    -0.40
     assai
    -0.40
     thereof
    -0.40
    OGND
    -0.39
     shall
    -0.38
    将在
    -0.38
    與
    -0.38
    POSITIVE LOGITS
     plufieurs
    0.63
    下手
    0.56
    自己
    0.55
     particulières
    0.54
     Pakai
    0.53
    三四
    0.51
     constitución
    0.51
     estratégica
    0.51
     competitivos
    0.51
    ~~
    0.51
    Activations Density 0.008%

    No Known Activations