© 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. 14867
    Prev
    Next
    INDEX
    Explanations

    links and URLs within the text

    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
    DeleteBehavior
    -0.65
    invokeLater
    -0.63
    VersionUID
    -0.62
     dima
    -0.56
    Ārējās
    -0.56
     yyb
    -0.56
    AutoScaleMode
    -0.56
     Lumpur
    -0.56
    profen
    -0.54
    MockMvc
    -0.53
    POSITIVE LOGITS
     facilmente
    0.68
    例句
    0.67
    MENAFN
    0.64
    ynb
    0.61
    kuuta
    0.60
     يتيمه
    0.59
    
    0.58
    IActionResult
    0.57
     WebView
    0.55
    gonic
    0.55
    Activations Density 0.108%

    No Known Activations