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. 1-GEMMASCOPE-RES-16K
    6. 13520
    Prev
    Next
    INDEX
    Explanations

    phrases indicating existence or availability of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chwiliwch
    -0.84
    ValueStyle
    -0.81
    Hentet
    -0.73
     препратки
    -0.73
     ویکی‌پدی
    -0.72
     unknownFields
    -0.70
     censiti
    -0.65
    Gambas
    -0.63
    μμα
    -0.63
    AccessorTable
    -0.63
    POSITIVE LOGITS
    cdi
    0.47
    otheby
    0.46
    áng
    0.45
    ORIES
    0.43
    Johannes
    0.43
    bleib
    0.42
    ghijkl
    0.42
    transQ
    0.42
    Clik
    0.42
    roberto
    0.41
    Activations Density 0.135%

    No Known Activations