© 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. 4932
    Prev
    Next
    INDEX
    Explanations

    geographic and administrative references

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

    after partial or misspelled location names

    np_acts-logits-general · gemini-2.0-flash

    Aveyron, flavonoids, siliceous

    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
    AnchorStyles
    -0.65
    PreInfinity
    -0.55
    IContainer
    -0.49
     Infórmanos
    -0.47
     surla
    -0.47
    Portale
    -0.44
    ########.
    -0.43
    ernsey
    -0.43
     EconPapers
    -0.42
    GLP
    -0.42
    POSITIVE LOGITS
     Disney
    0.60
    Disney
    0.55
    岐阜
    0.54
     disney
    0.52
    Arizona
    0.52
    fahan
    0.50
     Fresno
    0.50
     Tyrone
    0.49
    Birmingham
    0.49
    Bav
    0.48
    Activations Density 1.355%

    No Known Activations