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 - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 11205
    Prev
    Next
    INDEX
    Explanations

    terms related to footwear and shoe characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setupUi
    -0.51
    bonucleic
    -0.49
    rophes
    -0.47
    SerializedName
    -0.46
     Burnet
    -0.46
    şen
    -0.46
    lorette
    -0.43
     Vierge
    -0.43
    ParallelGroup
    -0.43
     lank
    -0.43
    POSITIVE LOGITS
     shoes
    1.81
     Shoes
    1.61
     footwear
    1.51
    Shoes
    1.48
     shoe
    1.44
    shoes
    1.41
     boots
    1.38
     SHOES
    1.38
     Footwear
    1.34
     sandals
    1.27
    Activations Density 0.570%

    No Known Activations