© 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. 28-GEMMASCOPE-RES-16K
    11. 10370
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations and sites

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "in"

    np_acts-logits-general · gemini-2.0-flash

    in staple diet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     d
    -0.37
     lop
    -0.37
     bes
    -0.34
     Mit
    -0.33
     res
    -0.33
    pNode
    -0.32
     trans
    -0.32
     blood
    -0.32
     PA
    -0.32
    kante
    -0.32
    POSITIVE LOGITS
     '\\;'
    0.71
     InputDecoration
    0.64
    richTextPanel
    0.63
    UserScript
    0.62
     okolí
    0.62
     defaultstate
    0.59
    EndContext
    0.58
     OFDb
    0.58
     protoimpl
    0.56
     ModelExpression
    0.56
    Activations Density 0.379%

    No Known Activations