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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 9316
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to emergency preparedness and risk communication

    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
    ])->
    -0.69
     ever
    -0.65
    گیرد
    -0.64
    jątk
    -0.61
     }}"></
    -0.60
    ₂)
    -0.60
    <[
    -0.59
     Monfieur
    -0.59
    }],
    
    -0.59
     Efq
    -0.59
    POSITIVE LOGITS
    Искәрмәләр
    0.63
     kasarigan
    0.60
    yntaxException
    0.57
    الحياه
    0.56
    Šaltiniai
    0.56
    ContentAsync
    0.54
    Geplaatst
    0.53
    rrggbb
    0.52
    ulemon
    0.51
     Roskov
    0.50
    Activations Density 1.765%

    No Known Activations