© 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. 22-GEMMASCOPE-RES-16K
    6. 3128
    Prev
    Next
    INDEX
    Explanations

    terms related to agricultural practices and crop management

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

    Farming, crops, and agricultural practices

    np_acts-logits-general · gemini-2.0-flash

    farming and crop production

    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
    WebVitals
    -0.61
     ddelweddau
    -0.60
    Demografie
    -0.60
    idorm
    -0.59
    цездатний
    -0.57
    ViewFeatures
    -0.57
    GenerationType
    -0.52
    insee
    -0.51
     Photocase
    -0.50
    ectoria
    -0.50
    POSITIVE LOGITS
     كومونز
    0.63
     rotation
    0.58
     row
    0.56
     rangs
    0.55
     couverts
    0.55
    twimg
    0.54
     TILL
    0.54
    لينكات
    0.53
     rotations
    0.52
    VersionUID
    0.52
    Activations Density 0.229%

    No Known Activations