© 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. 11569
    Prev
    Next
    INDEX
    Explanations

    specific phrases indicating unexpected outcomes or conditions in studies or analyses

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

    function words and auxiliary-heavy grammatical scaffolding, especially marking subordinate clauses and passive/continuous “be” constructions.

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

    phrases describing something as typical, expected, or characteristic of a particular category or context.

    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
    RegressionTest
    -0.61
     Numerade
    -0.61
    WriteAttribute
    -0.47
    wnież
    -0.42
    StoryboardSegue
    -0.41
    TagMode
    -0.40
    verwijspagina
    -0.40
    WriteTagHelper
    -0.38
    GEBURTSDATUM
    -0.36
    InjectAttribute
    -0.36
    POSITIVE LOGITS
    .*")]
    0.57
     AssemblyTitle
    0.45
    scribers
    0.44
     /\.
    0.44
    shells
    0.42
    .}}
    0.42
     CURIAM
    0.42
    wps
    0.41
     esternos
    0.41
    这么多
    0.40
    Activations Density 0.234%

    No Known Activations