© 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. 20-GEMMASCOPE-RES-16K
    6. 7875
    Prev
    Next
    INDEX
    Explanations

    terms related to ecological and evolutionary dynamics among species

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

    Ecological/spatial relationships, community composition

    np_acts-logits-general · gemini-2.0-flash

    ecological community distribution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     déput
    -0.59
     Defect
    -0.57
    athyroid
    -0.53
    intios
    -0.52
     procé
    -0.52
     ExecuteAsync
    -0.51
     Constellation
    -0.51
    riez
    -0.51
    ineno
    -0.51
     оригіналу
    -0.51
    POSITIVE LOGITS
     ecological
    0.79
     ecologically
    0.77
     spatially
    0.69
    ecological
    0.65
     habitat
    0.65
     spatial
    0.62
     Ecological
    0.62
     anthropogenic
    0.61
     biotic
    0.60
     sensu
    0.60
    Activations Density 2.175%

    No Known Activations