© 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. 7480
    Prev
    Next
    INDEX
    Explanations

    terms indicating potentiality or conditions that could alter situations and statements

    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
     intStringLen
    -0.49
     leyendo
    -0.49
     lepší
    -0.46
     bailando
    -0.46
     funcionando
    -0.45
     trabajando
    -0.44
     kaldı
    -0.44
     romantique
    -0.44
     mejorando
    -0.44
     Longueur
    -0.44
    POSITIVE LOGITS
     be
    1.05
     have
    0.79
     come
    0.71
     receive
    0.69
     become
    0.67
     belong
    0.65
     succeed
    0.64
     entertain
    0.63
     migrate
    0.62
     diverge
    0.61
    Activations Density 0.339%

    No Known Activations