© 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. 1-GEMMASCOPE-RES-16K
    6. 2209
    Prev
    Next
    INDEX
    Explanations

    the word "Is" and its variations, indicating a focus on identifying questions or statements related to existence or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.74
    ttemberg
    -0.67
    bootstrapcdn
    -0.64
     CURIAM
    -0.64
    Портали
    -0.63
     valueForKey
    -0.62
    yntaxException
    -0.62
     Autorizaciones
    -0.62
     zwiſchen
    -0.61
    GTCX
    -0.60
    POSITIVE LOGITS
     is
    2.41
     Is
    2.27
     IS
    1.91
    Is
    1.86
    is
    1.66
     ist
    1.13
     getIs
    1.10
     isa
    1.03
    setIs
    1.00
     isn
    0.98
    Activations Density 0.712%

    No Known Activations