© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 4229
    Prev
    Next
    INDEX
    Explanations

    phrases that express an overall assessment or summary

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

    "overall."

    np_acts-logits-general · gemini-2.0-flash

    overall

    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
    Биография
    -0.51
     FetchType
    -0.48
    zib
    -0.47
     Dungeons
    -0.47
     dentists
    -0.47
     dungeons
    -0.46
     photons
    -0.45
    ⓧ
    -0.45
    titutions
    -0.44
    FieldDescriptor
    -0.44
    POSITIVE LOGITS
     overall
    2.14
    Overall
    2.09
     Overall
    2.03
    overall
    2.02
    OVERALL
    1.62
    整體
    1.34
    整体
    1.23
    总体
    1.13
     keseluruhan
    1.08
    全体の
    1.08
    Activations Density 0.155%

    No Known Activations