© 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. 20-GEMMASCOPE-RES-16K
    11. 15464
    Prev
    Next
    INDEX
    Explanations

    HTML tags and structure within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Token "p" in HTML paragraph tags

    np_acts-logits-general · gemini-2.0-flash

    HTML paragraph and link tags

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ConstraintMaker
    -0.87
     houſe
    -0.84
    TestingModule
    -0.81
     ExecuteAsync
    -0.80
    endphp
    -0.80
    kloped
    -0.79
     Majefty
    -0.79
    rungsseite
    -0.77
     reaſon
    -0.75
    RegistryLite
    -0.75
    POSITIVE LOGITS
    ַת
    0.52
    målet
    0.51
    ')}}">
    0.40
     The
    0.38
     accro
    0.37
     Finally
    0.37
    horn
    0.37
    LOYEES
    0.36
     Stopping
    0.36
    FINALLY
    0.36
    Activations Density 0.090%

    No Known Activations