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. 12018
    Prev
    Next
    INDEX
    Explanations

    sections of the text that indicate significant data or important differentiations

    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
    ValueStyle
    -0.91
    herjee
    -0.91
    CloseOperation
    -0.90
    esseract
    -0.89
    rrggbb
    -0.83
     Spectre
    -0.83
     Saks
    -0.80
     maca
    -0.79
    Vere
    -0.79
     Heere
    -0.79
    POSITIVE LOGITS
    </h2>
    1.58
    "})
    0.94
    </h1>
    0.91
    "])
    0.90
    </th>
    0.90
    }")
    0.87
    "))
    0.85
    ");
    0.82
    })
    0.82
    ")]
    0.82
    Activations Density 0.034%

    No Known Activations