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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7920
    Prev
    Next
    INDEX
    Explanations

    terms related to geological or environmental surveying methodologies

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

    Erosion and river morphology

    np_acts-logits-general · gemini-2.0-flash

    soil erosion and surface runoff

    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
     للمعارف
    -0.76
    mybatisplus
    -0.73
     iVar
    -0.72
    reactstrap
    -0.61
     FetchType
    -0.58
     становника
    -0.55
     nadar
    -0.54
    hiza
    -0.54
     useAuth
    -0.53
     Raff
    -0.53
    POSITIVE LOGITS
     ero
    0.87
     erosion
    0.76
     Ero
    0.71
    Ero
    0.70
     slope
    0.63
     wash
    0.61
     landslide
    0.60
     Erosion
    0.60
    ero
    0.60
     eroded
    0.57
    Activations Density 0.200%

    No Known Activations