© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10940
    Prev
    Next
    INDEX
    Explanations

    dialogues and quotes from individuals

    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
     said
    -1.17
    Said
    -0.93
     Said
    -0.85
    said
    -0.78
     faid
    -0.74
     SAID
    -0.72
     stated
    -0.66
     gesagt
    -0.62
     dikatakan
    -0.61
     sagte
    -0.57
    POSITIVE LOGITS
     says
    1.77
    Says
    1.37
     say
    1.35
    says
    1.34
     Says
    1.28
    say
    1.13
     SAYS
    1.12
     говорит
    1.09
     fays
    1.06
     säger
    1.05
    Activations Density 0.453%

    No Known Activations