© 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. 10196
    Prev
    Next
    INDEX
    Explanations

    questions and their corresponding responses or answers

    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
    それでも
    -0.65
     therefore
    -0.58
    writeFieldEnd
    -0.51
     nonetheless
    -0.49
     Therefore
    -0.49
    therefore
    -0.48
     asimismo
    -0.48
     inoltre
    -0.47
    TemporalType
    -0.47
     nevertheless
    -0.47
    POSITIVE LOGITS
    Actually
    1.16
     Nope
    1.10
    Nope
    1.10
     Actually
    1.09
     actually
    1.06
    actually
    1.05
     nope
    0.99
    Depends
    0.93
    Absolutely
    0.91
    nope
    0.90
    Activations Density 0.429%

    No Known Activations