© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 11762
    Prev
    Next
    INDEX
    Explanations

    phrases indicating temporal or contextual limitations

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

    "Within" followed by a determiner

    np_acts-logits-general · gemini-2.0-flash

    defining a specific context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     obicei
    -0.54
     gewöhnlich
    -0.52
     teuer
    -0.48
    CppCodeGen
    -0.46
     vaiz
    -0.46
    chieht
    -0.45
     avoient
    -0.45
    __(/*!
    -0.44
    parsedMessage
    -0.44
     deswegen
    -0.43
    POSITIVE LOGITS
     within
    2.09
    within
    2.06
    Within
    2.05
     Within
    2.00
     WITHIN
    1.91
     innerhalb
    1.53
     dentro
    1.49
    Dentro
    1.48
     Dentro
    1.43
    dentro
    1.38
    Activations Density 0.146%

    No Known Activations