© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27862
    Prev
    Next
    INDEX
    Explanations

    descriptions of fashion items and their attributes

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

    neutral color, test, exists, [@B

    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
    DataAnnotations
    -0.51
    flich
    -0.48
     heraus
    -0.45
    ثيق
    -0.44
    onate
    -0.44
     vandens
    -0.43
     vettoriale
    -0.43
    cillor
    -0.43
    kema
    -0.42
    acrylamide
    -0.42
    POSITIVE LOGITS
     neutrals
    0.73
     staple
    0.72
    .*")]
    0.71
     Everyday
    0.68
     staples
    0.67
     khaki
    0.66
     InputDecoration
    0.65
     timeless
    0.65
     overcast
    0.65
     drab
    0.63
    Activations Density 0.063%

    No Known Activations