© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 12043
    Prev
    Next
    INDEX
    Explanations

    quantifiable aspects of trails and pathways

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

    Numbers close to zero

    np_acts-logits-general · gemini-2.0-flash

    quantities or precise measurements

    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
    +#+#
    -0.99
     betweenstory
    -0.86
    parsedMessage
    -0.83
    mergeFrom
    -0.81
     فريبيس
    -0.81
     تضيفلها
    -0.77
    MemoryWarning
    -0.71
    帖最后由
    -0.70
    WireFormatLite
    -0.67
    featureID
    -0.67
    POSITIVE LOGITS
     (.
    1.53
     .
    1.51
    (.
    1.38
    =.
    1.27
     ½
    1.27
     half
    1.20
    /.
    1.19
    -.
    1.17
     ¼
    1.16
     $.
    1.15
    Activations Density 0.797%

    No Known Activations