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. 7852
    Prev
    Next
    INDEX
    Explanations

    terms and references related to plants and plant materials

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

    plants

    np_acts-logits-general · gemini-2.0-flash

    plant species and diversity

    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
     Roskov
    -0.78
    WebVitals
    -0.77
    MemoryWarning
    -0.76
    ︎
    -0.72
    ableness
    -0.66
    --)
    
    -0.66
    
    -0.66
    terness
    -0.65
    }],
    
    -0.64
    OGND
    -0.63
    POSITIVE LOGITS
     species
    0.66
    life
    0.55
     Species
    0.54
     kingdom
    0.53
     life
    0.53
     matter
    0.53
     Kingdom
    0.50
    growing
    0.50
     SPECIES
    0.49
     growing
    0.49
    Activations Density 0.139%

    No Known Activations