© 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. 2-GEMMASCOPE-RES-16K
    6. 2463
    Prev
    Next
    INDEX
    Explanations

    words related to software implementation and code structure

    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
     entertained
    -0.83
     entertain
    -0.78
    Portale
    -0.68
    ensive
    -0.61
     McGovern
    -0.60
     Olímpicos
    -0.60
    بوابة
    -0.59
     entertainment
    -0.59
    ########.
    -0.59
     entertaining
    -0.59
    POSITIVE LOGITS
    impl
    1.30
    Impl
    1.02
     Révolution
    0.77
     impl
    0.74
     CiNii
    0.66
    IMPL
    0.66
     quæ
    0.65
    ServiceImpl
    0.65
    DebuggerNonUser
    0.64
    DAOImpl
    0.64
    Activations Density 0.062%

    No Known Activations