© 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. 5-GEMMASCOPE-RES-16K
    6. 6631
    Prev
    Next
    INDEX
    Explanations

    references to rain and related weather phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gemeinsame
    -0.53
    荡
    -0.53
    gerald
    -0.52
    حة
    -0.50
    rosz
    -0.48
     faro
    -0.46
    getTop
    -0.46
    ubar
    -0.46
    壯
    -0.46
     Toolbar
    -0.45
    POSITIVE LOGITS
     rain
    2.43
     rains
    2.22
     Rain
    2.17
    Rain
    2.12
     RAIN
    2.10
     rained
    1.96
     rainfall
    1.86
     raining
    1.81
     rainy
    1.72
    rain
    1.69
    Activations Density 0.079%

    No Known Activations