© 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. 3865
    Prev
    Next
    INDEX
    Explanations

    keywords related to order and state management in a database or structured data context

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

    database field names and identifiers in code (such as column names, table names, and variable names).

    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
    tagHelperRunner
    -1.08
    featureID
    -0.95
     OMITBAD
    -0.92
    цездатний
    -0.90
    RegressionTest
    -0.84
    parsedMessage
    -0.82
     <<<<<<<<<<<<<<
    -0.80
     nakalista
    -0.80
    GEBURTSDATUM
    -0.79
    UnusedPrivate
    -0.78
    POSITIVE LOGITS
    _
    0.39
    type
    0.35
    .
    0.33
     type
    0.32
     VARCHAR
    0.32
     varchar
    0.30
    g
    0.29
    name
    0.29
    fahrzeug
    0.29
    str
    0.28
    Activations Density 0.502%

    No Known Activations