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. 21-GEMMASCOPE-RES-16K
    6. 3005
    Prev
    Next
    INDEX
    Explanations

    numerical values representing measurements or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </th>
    -0.62
     </
    -0.62
     &
    -0.60
    </td>
    -0.59
     <
    -0.58
     ',
    -0.58
                                   
    -0.57
     $$
    -0.56
     is
    -0.56
     =
    -0.55
    POSITIVE LOGITS
     Reſ
    0.92
     pleaſure
    0.92
     myſelf
    0.92
     greateſt
    0.91
     Eſ
    0.90
     Anſ
    0.89
     beſt
    0.86
     juſt
    0.85
     Jefus
    0.84
     anſ
    0.84
    Activations Density 0.066%

    No Known Activations