© 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-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 27401
    Prev
    Next
    INDEX
    Explanations

    instances of the letter 'c' and its variations in capitalization

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

    variable names and mathematical constants like c

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.80
     CanadaChoose
    -0.77
    OSSARY
    -0.76
    .}~\
    -0.75
     themſelves
    -0.75
     ſind
    -0.75
     Patria
    -0.74
     doubtnut
    -0.74
     bezeichneter
    -0.74
    :][
    -0.73
    POSITIVE LOGITS
     C
    1.40
    C
    1.27
     getC
    1.16
     c
    1.13
    c
    1.02
    pC
    0.91
     corações
    0.91
    setC
    0.91
    getC
    0.84
    xC
    0.83
    Activations Density 0.211%

    No Known Activations