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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 11092
    Prev
    Next
    INDEX
    Explanations

    terms related to chemical reactions and synthesis processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    chemical synthesis

    np_acts-logits-general · gemini-2.0-flash

    synthesis and compounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.60
     SqlCommand
    -0.59
     metav
    -0.55
     Physica
    -0.53
    
    -0.51
    LLocation
    -0.50
    udesta
    -0.50
    appspot
    -0.49
     Adjutant
    -0.47
     NSCoder
    -0.47
    POSITIVE LOGITS
     Synthesis
    0.76
     synthesis
    0.76
     synthetic
    0.76
     synthesize
    0.73
     compounds
    0.72
    Synthesis
    0.71
     synthesized
    0.70
     chemistry
    0.69
     chemin
    0.67
     합
    0.67
    Activations Density 1.180%

    No Known Activations