© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 8328
    Prev
    Next
    INDEX
    Explanations

    phrases indicating claims or statements about actions and responsibilities

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

    "that"

    np_acts-logits-general · gemini-2.0-flash

    clauses introduced by that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
    CppMethod
    -0.88
    writeFieldEnd
    -0.75
     صوتيه
    -0.75
    tagext
    -0.72
    Autoritní
    -0.71
    sizeCache
    -0.69
     autorytatywna
    -0.68
    RenderAtEndOf
    -0.68
     OFDb
    -0.66
    UrlResolution
    -0.66
    POSITIVE LOGITS
     bahwa
    0.45
     that
    0.41
     ότι
    0.40
     bahawa
    0.39
     dass
    0.39
    ว่า
    0.38
     there
    0.37
     rằng
    0.36
     daß
    0.32
     أن
    0.31
    Activations Density 0.370%

    No Known Activations