Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 14176
    Prev
    Next
    INDEX
    Explanations

    references to the name "Har" and its variations in spelling

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

    Text containing "Har" followed by two letters

    np_acts-logits-general · gemini-2.0-flash

    HarMV, Harasty, Harun, Harve, Harrigan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EDEFAULT
    -0.60
     приш
    -0.55
     виправивши
    -0.54
     sumpay
    -0.53
    abestanden
    -0.52
    cô
    -0.48
     species
    -0.47
     socks
    -0.47
    AdapterView
    -0.46
     mergeFrom
    -0.46
    POSITIVE LOGITS
     BorderRadius
    0.59
    GEBURTSDATUM
    0.56
     الرياضيه
    0.55
    NameInMap
    0.55
    Geplaatst
    0.54
    InputBorder
    0.54
     Har
    0.53
    binger
    0.52
    rungsseite
    0.51
     har
    0.51
    Activations Density 0.111%

    No Known Activations