© 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. 2689
    Prev
    Next
    INDEX
    Explanations

    terms related to geometry and structure, particularly those involving "shoulder" and "edge"

    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
    ionView
    -0.38
    moveToFirst
    -0.34
     gorą
    -0.34
     любят
    -0.33
    ality
    -0.33
     mají
    -0.33
     gefördert
    -0.32
    omitempty
    -0.31
     olmak
    -0.31
     belangrij
    -0.31
    POSITIVE LOGITS
    Math
    0.74
     edge
    0.73
    tagHelperRunner
    0.72
     shoulder
    0.72
     Edge
    0.66
    shoulder
    0.66
     EDGE
    0.66
     betweenstory
    0.66
     WEATHER
    0.65
    Shoulder
    0.65
    Activations Density 0.113%

    No Known Activations