© 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. 2-GEMMASCOPE-RES-16K
    11. 6412
    Prev
    Next
    INDEX
    Explanations

    various combinations and forms of the word "Crafters" related to creative work

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Geist
    -0.56
     McGrath
    -0.54
     Rauch
    -0.54
     Brunnen
    -0.53
     Schatz
    -0.53
     Ofen
    -0.53
     Teich
    -0.52
     Blatt
    -0.50
     Kupfer
    -0.50
    opold
    -0.49
    POSITIVE LOGITS
     Cra
    1.16
     Sli
    1.13
     Dri
    1.13
     Stri
    1.13
    Cra
    1.12
    Sli
    1.09
     Sna
    1.08
     Gri
    1.06
     Gro
    1.06
     Sco
    1.05
    Activations Density 0.544%

    No Known Activations