© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3048
    Prev
    Next
    INDEX
    Explanations

    comments in code

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    comment markers in source code (such as `//` at the beginning of lines).

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Bronnen
    -0.62
     AttributeSet
    -0.59
    AddTagHelper
    -0.58
     становника
    -0.56
    InjectMocks
    -0.55
    IUrlHelper
    -0.54
    openzeppelin
    -0.54
     useAppContext
    -0.53
    twimg
    -0.52
     createState
    -0.52
    POSITIVE LOGITS
     //
    0.80
    //
    0.79
    TODO
    0.75
    ("//
    0.74
    "//
    0.73
    ,//
    0.68
     TODO
    0.67
    );//
    0.67
     "//
    0.66
    )//
    0.65
    Activations Density 0.086%

    No Known Activations