© 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. 2-GEMMASCOPE-RES-16K
    11. 14842
    Prev
    Next
    INDEX
    Explanations

    the concept of "something" or "someone" as a central theme in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     demais
    -0.57
     haul
    -0.56
    ibald
    -0.56
    IsPostBack
    -0.54
     Wikimédia
    -0.53
    pch
    -0.52
    WriteBarrier
    -0.52
    cửa
    -0.52
     totalSupply
    -0.52
    دارة
    -0.52
    POSITIVE LOGITS
     something
    2.82
    something
    2.73
    Something
    2.66
     Something
    2.58
     SOMETHING
    2.19
     somethin
    1.95
     quelque
    1.67
     qualcosa
    1.64
     något
    1.62
     algo
    1.62
    Activations Density 0.116%

    No Known Activations