© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 16044
    Prev
    Next
    INDEX
    Explanations

    phrases related to monoclonal antibodies and their applications in research or diagnosis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    extAlignment
    -0.88
     BoxFit
    -0.83
    RenderAtEndOf
    -0.77
     متعلقه
    -0.76
     <=",
    -0.75
     bezeichneter
    -0.74
     wireType
    -0.71
    сылкі
    -0.70
    pédie
    -0.69
     linkovi
    -0.68
    POSITIVE LOGITS
     antibodies
    1.55
     antibody
    1.34
     Antibodies
    1.34
    Antibodies
    1.19
     Antibody
    1.02
    anti
    0.99
     anti
    0.98
     monoclonal
    0.94
    Antibody
    0.93
     IgG
    0.89
    Activations Density 0.940%

    No Known Activations