© 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. 30-GEMMASCOPE-RES-16K
    11. 12581
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or entities, particularly in the context of academic works and publications

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

    starting with "Ho" (case-insensitive)

    np_acts-logits-general · gemini-2.0-flash

    words starting with ho

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    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
    -0.48
    ValueStyle
    -0.47
     Inverse
    -0.46
     ब्रेकडाउन
    -0.44
    Cyfeiriadau
    -0.42
     inverse
    -0.41
    UnsafeEnabled
    -0.39
    InnerText
    -0.38
    يميديا
    -0.38
    Datuak
    -0.37
    POSITIVE LOGITS
     Ho
    0.71
     ho
    0.68
    Ho
    0.66
     HO
    0.64
    ho
    0.55
     Hock
    0.53
     HOL
    0.51
    ホ
    0.51
    HO
    0.50
    astify
    0.47
    Activations Density 0.173%

    No Known Activations