Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 13883
    Prev
    Next
    INDEX
    Explanations

    instances of technical or mathematical notation

    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
     Theſe
    -0.65
     Zwie
    -0.64
     uſed
    -0.64
    پیوند
    -0.63
     ſaid
    -0.62
     ſhould
    -0.59
     fevere
    -0.57
    SafeArea
    -0.57
     duro
    -0.56
     blz
    -0.56
    POSITIVE LOGITS
    >{@
    1.00
    ']")
    0.83
    ViewFeatures
    0.83
     ③
    0.81
     ]);
    0.78
     }]
    0.77
     Савезне
    0.74
    '}>
    0.72
     *}
    0.72
    ″]
    0.72
    Activations Density 0.095%

    No Known Activations