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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19-GEMMASCOPE-RES-16K
    6. 3005
    Prev
    Next
    INDEX
    Explanations

    details about renovations and improvements in buildings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tracce
    -0.56
    ImageContext
    -0.52
    TestingModule
    -0.52
    İstinadlar
    -0.51
     censiti
    -0.50
    SizeF
    -0.50
    readAs
    -0.49
    primento
    -0.49
    جمعیت
    -0.47
     ankles
    -0.47
    POSITIVE LOGITS
     inside
    2.65
    inside
    2.41
     Inside
    2.38
    Inside
    2.35
     internal
    2.32
     interior
    2.19
     outside
    2.17
     INSIDE
    2.14
     internally
    2.14
    internal
    2.07
    Activations Density 0.457%

    No Known Activations