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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 13276
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and their values

    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
     propOrder
    -0.96
    fjspx
    -0.90
     يتيمه
    -0.87
     
    -0.86
    </em>
    -0.85
    xla
    -0.83
    UnsafeEnabled
    -0.81
    writeFieldEnd
    -0.80
    \{\\
    -0.78
    äksi
    -0.77
    POSITIVE LOGITS
    ='
    1.00
    ../
    0.88
    </b>
    0.81
     Bekasi
    0.79
    jgl
    0.78
    ORPG
    0.72
     Sharjah
    0.72
     Barrera
    0.69
    _{\
    0.69
     Griswold
    0.69
    Activations Density 0.113%

    No Known Activations