© 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
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 7538
    Prev
    Next
    INDEX
    Explanations

    legal references and case citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     محفوظة
    -0.40
     سكانية
    -0.36
    yarnpkg
    -0.34
    marginLeft
    -0.34
    npmjs
    -0.33
     InputDecoration
    -0.33
    Tikang
    -0.33
     atof
    -0.33
     noqa
    -0.33
    +#+#
    -0.32
    POSITIVE LOGITS
    -------
    0.81
    [toxicity=0]
    0.60
    ――――
    0.57
    UrlResolution
    0.57
     Wikiseite
    0.54
    ―――
    0.53
    XmlAccessorType
    0.52
     jsPsych
    0.52
    tvguidetime
    0.52
     ProtoMessage
    0.52
    Activations Density 2.019%

    No Known Activations