© 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. 2318
    Prev
    Next
    INDEX
    Explanations

    topics related to various types of containers and their elements

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

    organizational units or modules

    np_acts-logits-general · gemini-2.0-flash

    specific entities and their attributes

    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
    pecabe
    -0.42
     morada
    -0.39
     North
    -0.38
    Hehe
    -0.38
    WriteBarrier
    -0.38
    phoric
    -0.38
     navideña
    -0.36
    North
    -0.35
     étanche
    -0.35
    WriteAttribute
    -0.35
    POSITIVE LOGITS
     otomatig
    0.57
    pezif
    0.50
     resourceCulture
    0.47
     betweenstory
    0.47
    msgTypes
    0.46
     Specific
    0.46
     ModelExpression
    0.46
     specific
    0.44
    msford
    0.44
    pezifische
    0.44
    Activations Density 0.946%

    No Known Activations