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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 888
    Prev
    Next
    INDEX
    Explanations

    elements related to variety and selection in products or options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    exitRule
    -0.79
    AddTagHelper
    -0.75
    numerusform
    -0.66
     '\\;'
    -0.63
    ásra
    -0.63
    WriteTagHelper
    -0.58
    getColumnIndex
    -0.55
    writeFieldEnd
    -0.54
    posedge
    -0.54
     tartalomajánló
    -0.52
    POSITIVE LOGITS
     colors
    1.42
     styles
    1.39
     sizes
    1.37
     design
    1.34
     color
    1.33
     shape
    1.29
     colours
    1.27
     style
    1.27
     size
    1.27
     designs
    1.25
    Activations Density 0.287%

    No Known Activations