© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 14458
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and demographic statistics

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

    Tokens after colons, especially in technical contexts

    np_acts-logits-general · gemini-2.0-flash

    specific numbers and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     Administrativna
    -1.18
    ValueStyle
    -1.14
    
    -1.09
     الرياضيه
    -1.04
    featureID
    -1.03
    OGND
    -1.00
    Personensuche
    -0.97
    WebVitals
    -0.94
    Hentet
    -0.94
     Roskov
    -0.93
    POSITIVE LOGITS
     (
    0.50
     for
    0.47
    ,
    0.45
     meanwhile
    0.44
    ，
    0.43
    __(/*!
    0.43
     from
    0.42
     alleging
    0.42
    ،
    0.42
    等
    0.42
    Activations Density 0.936%

    No Known Activations