© 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 - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 8953
    Prev
    Next
    INDEX
    Explanations

    references to chemical properties and interactions related to materials science

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     things
    -0.69
     thing
    -0.69
     coisas
    -0.65
     something
    -0.61
     cosas
    -0.60
     you
    -0.58
     qualcosa
    -0.57
     davvero
    -0.57
     coisa
    -0.55
     pezzo
    -0.55
    POSITIVE LOGITS
    __':
    
    1.07
    __':
    1.03
     препратки
    1.01
     betweenstory
    1.00
    RectangleBorder
    0.99
    )':
    0.98
    Geplaatst
    0.96
    GEBURTSDATUM
    0.95
    WithIOException
    0.95
    StructEnd
    0.93
    Activations Density 3.119%

    No Known Activations