© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 11190
    Prev
    Next
    INDEX
    Explanations

    repeated phrases that indicate location or presence

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

    Text referring to a particular place or location

    np_acts-logits-general · gemini-2.0-flash

    locations followed by other words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.68
     kaarangay
    -0.63
    Vidite
    -0.60
    CommandText
    -0.58
    RTSC
    -0.58
    setVerticalGroup
    -0.57
    keyColumn
    -0.56
    enderror
    -0.53
     createSlice
    -0.52
    割
    -0.51
    POSITIVE LOGITS
     where
    0.73
     שם
    0.65
     Allí
    0.61
     где
    0.59
    Where
    0.56
     ahol
    0.56
     donde
    0.56
     Where
    0.55
     nơi
    0.55
     όπου
    0.54
    Activations Density 0.310%

    No Known Activations