© 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. 4-GEMMASCOPE-RES-16K
    6. 16170
    Prev
    Next
    INDEX
    Explanations

    references to the size of objects or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thanol
    -0.64
    Portale
    -0.63
    endregion
    -0.63
     سكانية
    -0.62
    colhead
    -0.62
     blé
    -0.61
    abstractmethod
    -0.61
    有任何
    -0.60
    Penta
    -0.60
    opard
    -0.60
    POSITIVE LOGITS
     size
    2.55
     SIZE
    2.35
     Size
    2.25
     sizes
    2.17
    size
    2.11
    Size
    2.05
    SIZE
    2.02
     Sizes
    1.82
     sizing
    1.76
     sized
    1.76
    Activations Density 0.110%

    No Known Activations