© 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. 1-GEMMASCOPE-RES-16K
    6. 5699
    Prev
    Next
    INDEX
    Explanations

    function definitions and declarations in a programming context, particularly related to session and language management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.90
    IUrlHelper
    -0.88
     tartalomajánló
    -0.87
    tvguidetime
    -0.86
     '\\;'
    -0.80
    ]))
    
    -0.80
    ImageContext
    -0.79
     дописавши
    -0.79
    WithMany
    -0.79
    errHandler
    -0.78
    POSITIVE LOGITS
    gaard
    0.43
     emin
    0.41
     Gu
    0.40
     Netz
    0.39
    čius
    0.38
     type
    0.38
     bezeichnet
    0.37
    ;
    0.37
    不可
    0.37
    안
    0.37
    Activations Density 0.300%

    No Known Activations