Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 53439
    Prev
    Next
    INDEX
    Explanations

    quantifiable metrics related to frequency and time

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

    time and frequency

    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
    évaluateur
    -0.87
     tartalomajánló
    -0.82
    
    -0.78
     المعيارى
    -0.75
     мәкал
    -0.75
     समीक्षाओं
    -0.74
    )|^{
    -0.69
     TextAppearance
    -0.66
    nachron
    -0.66
    ntlet
    -0.64
    POSITIVE LOGITS
     they
    0.97
     we
    0.84
     he
    0.66
     you
    0.65
     she
    0.59
     они
    0.58
     оно
    0.52
     it
    0.50
     that
    0.48
     oprot
    0.47
    Activations Density 0.213%

    No Known Activations