Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 13453
    Prev
    Next
    INDEX
    Explanations

    descriptions of skin conditions or lesions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.54
    ագրություններ
    -0.54
    });*/
    -0.53
     cannibal
    -0.52
     zwy
    -0.52
     fieldNum
    -0.51
    })();
    
    -0.51
    tagHelperRunner
    -0.51
    raus
    -0.50
     Saeed
    -0.50
    POSITIVE LOGITS
     chest
    1.17
     neck
    1.09
     abdomen
    1.09
     Chest
    0.89
    chest
    0.88
     belly
    0.87
     upper
    0.86
     forehead
    0.85
     thigh
    0.85
     shoulder
    0.84
    Activations Density 0.398%

    No Known Activations