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 - 131k
    5. 33-GEMMASCOPE-RES-131K
    6. 65820
    Prev
    Next
    INDEX
    Explanations

    references to biological treatments and their effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     duro
    -0.33
    Décès
    -0.33
    ofday
    -0.32
    .*")]
    -0.32
     đẩy
    -0.32
    diet
    -0.31
    硬
    -0.31
     }}"></
    -0.31
     verbre
    -0.30
     feeding
    -0.30
    POSITIVE LOGITS
     monoclonal
    0.80
     biolog
    0.76
     antibodies
    0.74
     antibody
    0.74
     biologic
    0.71
    Antibody
    0.68
     Antibodies
    0.68
     Antibody
    0.66
    Antibodies
    0.64
     recombinant
    0.63
    Activations Density 0.160%

    No Known Activations