© 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. 13878
    Prev
    Next
    INDEX
    Explanations

    Java classes and their implementations specifically related to statistical and mathematical operations

    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
    Personendaten
    -0.73
     Snackbar
    -0.72
    moveToFirst
    -0.70
     AppCompatTheme
    -0.69
     Maro
    -0.68
    Revenir
    -0.66
    MessageOf
    -0.66
    moveToNext
    -0.65
    providedIn
    -0.65
    ($__
    -0.65
    POSITIVE LOGITS
    impl
    2.59
    Impl
    2.50
     impl
    1.83
    IMPL
    1.81
    ServiceImpl
    1.70
    DaoImpl
    1.54
    DAOImpl
    1.47
     Implant
    1.34
     Imp
    1.29
     implantation
    1.28
    Activations Density 0.076%

    No Known Activations