© 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. 24-GEMMASCOPE-RES-16K
    11. 1138
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and products related to tools and devices

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

    Follows capital letters or numbers

    np_acts-logits-general · gemini-2.0-flash

    Locking pliers, Xerography, denominations, nationality

    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
     uParam
    -0.57
    IVEREF
    -0.51
     iParam
    -0.50
     nakalista
    -0.49
    RTSN
    -0.48
     المعيارى
    -0.48
     виправивши
    -0.48
    mybatisplus
    -0.46
     Expédié
    -0.45
     vixion
    -0.45
    POSITIVE LOGITS
    :✨
    0.52
    OPA
    0.35
    ファースト
    0.34
     maglia
    0.33
    hermes
    0.32
     CVC
    0.32
    ⇑
    0.32
    })));
    0.31
     DPD
    0.31
    OGN
    0.31
    Activations Density 0.835%

    No Known Activations