© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 17381
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically focusing on surnames

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

    Norton, Morton, Horton, Easton

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ransition
    -0.53
    endphp
    -0.51
    moveToFirst
    -0.45
    プライズ
    -0.45
     setId
    -0.44
     Schwangerschaft
    -0.44
    deepcopy
    -0.44
    chrän
    -0.43
     Gier
    -0.43
     kjem
    -0.43
    POSITIVE LOGITS
     Norton
    2.81
    Norton
    2.66
     Nort
    1.27
    orton
    1.12
     NOR
    1.00
    mantec
    0.99
     Horton
    0.84
    NOR
    0.82
     Morton
    0.71
     Norte
    0.69
    Activations Density 0.002%

    No Known Activations