© 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. 8-GEMMASCOPE-RES-16K
    11. 11601
    Prev
    Next
    INDEX
    Explanations

    references to mathematical properties and transformations related to linearity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MotionEvent
    -0.50
    PropertyChanging
    -0.46
     Membran
    -0.44
     remercie
    -0.41
    束
    -0.41
    łosi
    -0.40
     médicaux
    -0.39
     ц
    -0.38
    firm
    -0.37
    עה
    -0.37
    POSITIVE LOGITS
    tagHelperRunner
    0.88
    rrggbb
    0.85
    ftagPool
    0.78
    queryInterface
    0.77
     الحره
    0.75
     pinulongan
    0.74
    ]")]
    0.73
    
    0.72
     typelib
    0.72
    SourceChecksum
    0.69
    Activations Density 0.945%

    No Known Activations