© 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. 20-GEMMASCOPE-RES-16K
    11. 13653
    Prev
    Next
    INDEX
    Explanations

    concepts related to evolution and social identity

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

    metalinguistic references to terms or labels—especially when something is defined, called, or discussed as a “so‑called” concept, often set off in quotation marks.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    words or phrases enclosed in quotation marks that are being defined, labeled, or characterized as misnomers or terms with contested meanings.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.67
    extAlignment
    -0.61
     Autorisations
    -0.60
     CURIAM
    -0.59
     TextAlign
    -0.57
    jolly
    -0.54
    InitVars
    -0.54
    ➟
    -0.53
    Vidite
    -0.53
     CreateTagHelper
    -0.53
    POSITIVE LOGITS
     onCreateView
    0.36
    zeera
    0.32
    ">//
    0.31
     intptr
    0.31
     egentlig
    0.29
     AssemblyTitle
    0.29
     navnet
    0.29
     namanya
    0.29
     itself
    0.28
     really
    0.28
    Activations Density 0.443%

    No Known Activations