© 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 EvalsExportsAPI 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. 6813
    Prev
    Next
    INDEX
    Explanations

    sentences that contain actions or events related to reading and writing

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

    Follows a conjunction

    np_acts-logits-general · gemini-2.0-flash

    further by incorporating

    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
    ſchaft
    -0.47
    ViewInit
    -0.46
    iſchen
    -0.46
    niſſe
    -0.44
    ようやく
    -0.44
    matchCondition
    -0.43
    씩
    -0.42
     ddelwed
    -0.41
     endregion
    -0.41
    retudo
    -0.40
    POSITIVE LOGITS
     further
    1.03
     weiteren
    0.95
     continuing
    0.94
     weitere
    0.94
     continued
    0.92
    further
    0.87
     Further
    0.86
    Further
    0.85
     дальней
    0.85
     weiterer
    0.85
    Activations Density 0.773%

    No Known Activations