© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 3369
    Prev
    Next
    INDEX
    Explanations

    mathematical constructs and symbols associated with set notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orra
    -0.61
    als
    -0.53
     your
    -0.51
    ientôt
    -0.49
     zul
    -0.48
    ist
    -0.47
    bear
    -0.46
    ederen
    -0.46
     pu
    -0.46
    役
    -0.46
    POSITIVE LOGITS
    Portale
    1.07
    ^(@)
    1.01
    %");
    0.88
     utafitiHapana
    0.87
    berdayakan
    0.84
     colorWith
    0.84
    CppCodeGen
    0.83
     Efq
    0.83
    AsUp
    0.82
     ?</
    0.82
    Activations Density 0.274%

    No Known Activations