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. 11-GEMMASCOPE-RES-16K
    6. 6174
    Prev
    Next
    INDEX
    Explanations

    dates and numeric references related to events or occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.84
    pidou
    -0.78
    saraba
    -0.69
    prefixer
    -0.68
    клопе
    -0.65
     كومونز
    -0.65
     MonoBehaviour
    -0.65
    下载附件
    -0.64
     незавершена
    -0.63
    InjectAttribute
    -0.63
    POSITIVE LOGITS
     확인함
    0.57
     heller
    0.53
     also
    0.51
     proprement
    0.49
     myös
    0.48
     itself
    0.47
     remise
    0.47
     only
    0.46
     stesso
    0.46
    subplots
    0.44
    Activations Density 0.141%

    No Known Activations