© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 31-GEMMASCOPE-RES-16K
    11. 11248
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or places, especially the word "here."

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

    the word "here" as a standalone locational reference.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     here
    -0.86
     aici
    -0.67
     aquí
    -0.66
     ahí
    -0.63
     هنا
    -0.62
     disini
    -0.60
     здесь
    -0.59
     daarbij
    -0.57
     тут
    -0.57
     voici
    -0.54
    POSITIVE LOGITS
     مرئيه
    0.59
    principalColumn
    0.52
    RTEE
    0.50
    ValueStyle
    0.47
    under
    0.46
    zul
    0.46
     ProtoMessage
    0.46
     mismo
    0.45
    Diwedd
    0.45
    unto
    0.43
    Activations Density 0.142%

    No Known Activations