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. 13260
    Prev
    Next
    INDEX
    Explanations

    HTML tags for bold text formatting

    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
    """.
    -1.18
     
    -0.94
    {}",
    -0.87
     GenerationType
    -0.86
    """
    
    -0.84
    ",@"
    -0.81
    </strong>
    -0.80
    %";
    -0.78
    """)
    -0.78
    **/
    
    -0.78
    POSITIVE LOGITS
    <b>
    1.93
    </b>
    1.24
    </i>
    1.17
    <i>
    1.01
    <u>
    0.79
    dfrac
    0.70
     ${\
    0.67
    例文帳に追加
    0.61
    ${\
    0.53
     
    0.51
    Activations Density 0.015%

    No Known Activations