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. 13-GEMMASCOPE-RES-16K
    6. 14382
    Prev
    Next
    INDEX
    Explanations

    special characters or formatting details such as brackets or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    crollView
    -0.65
    VIRGO
    -0.64
    RRect
    -0.63
     InkWell
    -0.62
    LLocation
    -0.61
     dénon
    -0.61
     démission
    -0.60
    ién
    -0.59
    formKey
    -0.59
    fees
    -0.59
    POSITIVE LOGITS
    </em>
    1.49
    </u>
    1.19
    </strong>
    1.13
    </i>
    1.11
    </h5>
    0.99
    </h2>
    0.94
    </h4>
    0.89
    </code>
    0.89
    </h6>
    0.87
    }*/
    0.80
    Activations Density 0.138%

    No Known Activations