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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6641
    Prev
    Next
    INDEX
    Explanations

    HTML block elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
    EnableWeb
    -0.57
     fides
    -0.56
    lito
    -0.55
     pica
    -0.54
     CDS
    -0.54
    FLD
    -0.54
    ={<
    -0.54
     fluvial
    -0.53
     RIAA
    -0.53
    原始内容存档于
    -0.53
    POSITIVE LOGITS
    </blockquote>
    1.09
    \]
    0.77
     Audiodateien
    0.70
    </h5>
    0.64
    </h4>
    0.63
    </h2>
    0.59
    </h6>
    0.59
     iconLine
    0.57
    </h3>
    0.57
    }*/
    
    0.55
    Activations Density 0.245%

    No Known Activations