© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 39430
    Prev
    Next
    INDEX
    Explanations

    file paths, specifically those that start with "../"

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

    directory paths starting with ../

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     ujednoznacz
    -0.62
    ConstraintMaker
    -0.57
    ագրություններ
    -0.52
     Sequo
    -0.50
     Wikiseite
    -0.49
    bardier
    -0.49
     مرئيه
    -0.48
    erdings
    -0.48
    Addo
    -0.45
    droje
    -0.45
    POSITIVE LOGITS
     "../
    2.17
     "../../
    1.54
    "../
    1.47
     "../../../
    1.43
    ("../
    1.41
    ../
    1.37
    ="../
    1.27
     "../../../../
    1.21
     ../
    1.18
    ('../
    1.02
    Activations Density 0.005%

    No Known Activations