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. 14133
    Prev
    Next
    INDEX
    Explanations

    mathematical functions involving summation

    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
    '/>
    -0.77
    });*/
    -0.71
    };*/
    -0.71
    )*/
    -0.69
    ']->
    -0.69
    >>()
    -0.68
     Karak
    -0.68
    '>";
    -0.67
    ')['
    -0.66
    =""/>
    -0.66
    POSITIVE LOGITS
    sum
    2.30
    Sum
    2.25
     sum
    2.23
     Sum
    2.23
     SUM
    2.10
    SUM
    1.95
     sums
    1.89
    ∑
    1.64
     summation
    1.59
    Sums
    1.58
    Activations Density 0.110%

    No Known Activations