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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 12937
    Prev
    Next
    INDEX
    Explanations

    chemical substances and their compounds related to water and minerals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.76
    Pautan
    -0.70
     tartalomajánló
    -0.68
    Carcinogenicity
    -0.67
     externi
    -0.66
     صوتيه
    -0.66
    Parcelize
    -0.65
    іга
    -0.64
    SharedCtor
    -0.63
     "..\..\
    -0.61
    POSITIVE LOGITS
     water
    2.07
     Water
    1.90
    Water
    1.81
    water
    1.77
     WATER
    1.70
    WATER
    1.61
     agua
    1.50
     waters
    1.44
     água
    1.43
     Wasser
    1.37
    Activations Density 0.179%

    No Known Activations