© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 12712
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and citations

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

    legal citations in the format of case names followed by numerical references (e.g., U.S., F.2d, F.3d reporter abbreviations with page numbers).

    oai_token-act-pair · claude-4-5-haikuTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.65
    ConstraintMaker
    -0.62
     surla
    -0.56
    webElementXpaths
    -0.55
     typelib
    -0.54
    IntoConstraints
    -0.53
     recevrez
    -0.51
    Geplaatst
    -0.50
    featureID
    -0.50
     aimez
    -0.49
    POSITIVE LOGITS
    VIAF
    0.42
    ApiProperty
    0.38
    orgon
    0.36
     McC
    0.35
    cc
    0.32
     下午
    0.32
    nm
    0.32
     Baker
    0.31
    words
    0.31
     ISNI
    0.31
    Activations Density 1.412%

    No Known Activations