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. 23-GEMMASCOPE-RES-16K
    6. 11188
    Prev
    Next
    INDEX
    Explanations

    references to weather phenomena, especially involving snow and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Controllo
    -0.55
     Hotspot
    -0.52
     iulie
    -0.51
    кк
    -0.50
    ypep
    -0.50
    DockStyle
    -0.49
     CEST
    -0.48
    writeHead
    -0.47
     weaver
    -0.47
     Kog
    -0.47
    POSITIVE LOGITS
     snow
    2.25
     ice
    2.07
     frozen
    2.04
     freezing
    1.87
    snow
    1.83
     Snow
    1.83
     freeze
    1.82
    Snow
    1.77
     froze
    1.76
     snowfall
    1.75
    Activations Density 0.265%

    No Known Activations