© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 11496
    Prev
    Next
    INDEX
    Explanations

    key statements related to significant achievements or transformations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ंदीखरीदारी
    -0.57
    enumi
    -0.51
    IVEREF
    -0.49
    Stellar
    -0.48
     }}}{
    -0.47
    cassert
    -0.47
     Stellar
    -0.47
     كومونز
    -0.46
     resourceCulture
    -0.46
    tinyos
    -0.46
    POSITIVE LOGITS
     very
    0.44
    ckså
    0.42
    RuleContext
    0.42
     juridiques
    0.41
     démocr
    0.41
     Grecs
    0.40
     origines
    0.40
     enfans
    0.40
     esqueleto
    0.39
     patata
    0.39
    Activations Density 0.399%

    No Known Activations