© 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. 16-GEMMASCOPE-RES-16K
    11. 6834
    Prev
    Next
    INDEX
    Explanations

    the concept of uniqueness and innovative aspects across various contexts

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

    "unique" or its variations

    np_acts-logits-general · gemini-2.0-flash

    unique attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Inters
    -0.51
     termen
    -0.49
     predecess
    -0.49
     eşofman
    -0.49
     Scrolls
    -0.48
     Indon
    -0.48
     нат
    -0.48
    Để
    -0.47
     sobremesa
    -0.47
     rekla
    -0.47
    POSITIVE LOGITS
    unique
    1.09
     unique
    1.08
     UNIQUE
    1.07
    Unique
    1.04
     Unique
    1.01
     uniques
    1.00
    UNIQUE
    0.99
     uniquely
    0.96
     uniqu
    0.92
     uniqueness
    0.91
    Activations Density 0.129%

    No Known Activations