© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1667
    Prev
    Next
    INDEX
    Explanations

    specific technical terms related to image formats, programming concepts, and data management

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

    First word of a list of items

    np_acts-logits-general · gemini-2.0-flash

    all or etc

    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
    MigrationBuilder
    -0.78
    styleType
    -0.68
    enterOuterAlt
    -0.65
    httphttps
    -0.60
     ujednoznacz
    -0.58
    PRNewswire
    -0.58
     nahilalakip
    -0.54
     resourceCulture
    -0.54
     Beide
    -0.54
     beider
    -0.54
    POSITIVE LOGITS
     all
    0.65
     allemaal
    0.49
    all
    0.49
     etc
    0.46
     semuanya
    0.46
     kõik
    0.45
     kaikki
    0.43
     등
    0.42
     peuples
    0.42
    等等
    0.42
    Activations Density 0.705%

    No Known Activations