© 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. 24-GEMMASCOPE-RES-16K
    11. 5589
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting symbols in the text

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

    Hexadecimal representations and symbols

    np_acts-logits-general · gemini-2.0-flash

    code tags and structure

    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
    Personendaten
    -0.60
    IBarButtonItem
    -0.55
    NameInMap
    -0.54
    styleType
    -0.53
    ValueStyle
    -0.51
    enderror
    -0.50
    oredCriteria
    -0.45
     Wines
    -0.44
    Derbyniad
    -0.43
     мәгълү
    -0.42
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.51
     cowok
    0.43
    UnusedPrivate
    0.42
     connexes
    0.36
    nalités
    0.36
    abstractmethod
    0.35
    tagext
    0.35
    MemoryWarning
    0.35
     cewek
    0.34
     you
    0.34
    Activations Density 0.383%

    No Known Activations