© 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. 28391
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Har" in various contexts

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

    words starting with Har

    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
    pointe
    -0.60
     Boi
    -0.57
    zadeh
    -0.56
    tue
    -0.56
    tione
    -0.54
     '\\;'
    -0.53
    idia
    -0.53
     Crusoe
    -0.52
    ніципалі
    -0.52
    enheim
    -0.51
    POSITIVE LOGITS
     Har
    2.02
    Har
    1.86
     har
    1.51
     HAR
    1.41
    har
    1.39
    HAR
    1.32
     HARR
    1.05
     Harlan
    1.05
     Harrell
    1.03
     Хар
    1.02
    Activations Density 0.003%

    No Known Activations