© 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. 18-GEMMASCOPE-RES-16K
    11. 6114
    Prev
    Next
    INDEX
    Explanations

    expressions of personal reflections and emotions

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

    Follows certain verbs/words like "goes", "replaced," "matched", or "suppose"

    np_acts-logits-general · gemini-2.0-flash

    explaining lists and sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Meksiku
    -0.74
    
    -0.60
    !("{}",
    -0.58
     perfons
    -0.56
    nezeu
    -0.53
    AutoModerator
    -0.52
     Bourgoin
    -0.52
    TestTools
    -0.51
    indirizzo
    -0.51
     navíc
    -0.50
    POSITIVE LOGITS
     maybe
    0.60
     tartalomajánló
    0.58
     onOptions
    0.58
    awtextra
    0.56
    ConstraintMaker
    0.56
    BagConstraints
    0.54
     تضيفلها
    0.53
     propOrder
    0.52
    FunctionFlags
    0.51
     perhaps
    0.51
    Activations Density 0.372%

    No Known Activations