© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 8131
    Prev
    Next
    INDEX
    Explanations

    specific descriptors or characteristics of people or things, particularly focusing on contrasting traits

    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
    Autoritní
    -0.49
    GraphicsUnit
    -0.47
    jsxFileName
    -0.46
    OGND
    -0.43
     ISNI
    -0.41
    Chham
    -0.40
    setViewportView
    -0.40
     NSCoder
    -0.40
    IUrlHelper
    -0.39
    accessible
    -0.39
    POSITIVE LOGITS
     headed
    0.98
     faced
    0.91
     eyed
    0.84
     handed
    0.84
     voiced
    0.80
     skinned
    0.75
     footed
    0.74
     mout
    0.73
     legged
    0.73
    headed
    0.73
    Activations Density 0.492%

    No Known Activations