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. 3007
    Prev
    Next
    INDEX
    Explanations

    HTML elements and their attributes in a markup context

    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
     ]];
    -0.59
     AttributeSet
    -0.56
    endphp
    -0.54
    //
    -0.53
    setCellStyle
    -0.51
    AxisAlignment
    -0.50
    errHandler
    -0.49
     Salim
    -0.48
    IsTrue
    -0.48
    "];
    
    -0.48
    POSITIVE LOGITS
    "><
    1.24
    ><
    1.21
    '><
    1.15
    ."<
    0.94
    ?><
    0.93
     '<
    0.93
    =""><
    0.92
     ><
    0.91
    ;"><
    0.91
    ;<
    0.90
    Activations Density 0.173%

    No Known Activations