© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 2847
    Prev
    Next
    INDEX
    Explanations

    SQL queries and commands related to data selection, updating, and joining in databases

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

    SQL queries starting with "from" or "select"

    np_acts-logits-general · gemini-2.0-flash

    SQL SELECT FROM statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    -0.43
    ,
    -0.37
     and
    -0.35
    imageFile
    -0.35
    _
    -0.34
    +
    -0.30
    .
    -0.30
    /
    -0.30
     Pascual
    -0.30
    ↵↵
    -0.29
    POSITIVE LOGITS
    tvguidetime
    0.91
    kháu
    0.88
     snippetHide
    0.85
     Roskov
    0.84
     nakalista
    0.82
     <<<<<<<<<<<<<<
    0.81
    endphp
    0.81
    verwijspagina
    0.78
    sizeCache
    0.78
    exitRule
    0.78
    Activations Density 0.091%

    No Known Activations