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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 14052
    Prev
    Next
    INDEX
    Explanations

    concepts related to inheritance and passing down knowledge or traditions through generations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ciamento
    -0.52
     paraître
    -0.47
    isance
    -0.47
    FormTagHelper
    -0.46
     lunak
    -0.46
    uticos
    -0.46
     tege
    -0.44
    SOUNDBITE
    -0.43
    ьаж
    -0.42
     vilja
    -0.42
    POSITIVE LOGITS
     passed
    2.37
     pass
    2.31
     passing
    2.24
     passes
    2.12
     Passing
    2.08
     Passed
    2.07
    Passing
    2.07
     Pass
    2.00
    passed
    2.00
    pass
    1.95
    Activations Density 0.491%

    No Known Activations