© 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. 2-GEMMASCOPE-RES-16K
    11. 11706
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "scratch" and related terms indicating the concept of starting anew or from the beginning

    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
    MethodImpl
    -0.54
    awtextra
    -0.52
     estekak
    -0.52
    MockBean
    -0.51
    fjspx
    -0.48
    hamilan
    -0.48
     calcetines
    -0.48
    encodeWith
    -0.46
     pubblicità
    -0.44
     vacía
    -0.44
    POSITIVE LOGITS
     scratch
    1.16
     Scratch
    1.05
    scratch
    0.99
    Scratch
    0.90
     scratched
    0.87
     scratches
    0.79
     scratching
    0.76
     Scra
    0.69
     rub
    0.67
     scrat
    0.66
    Activations Density 0.282%

    No Known Activations