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. 15-GEMMASCOPE-RES-16K
    6. 12913
    Prev
    Next
    INDEX
    Explanations

    references to fog and related atmospheric phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    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
    -0.85
    #+#
    -0.78
     WaitForSeconds
    -0.70
     Acha
    -0.67
     levure
    -0.66
    hyth
    -0.65
     JpaRepository
    -0.65
    ⓧ
    -0.65
     للاسماء
    -0.64
    EndInit
    -0.64
    POSITIVE LOGITS
     cloud
    1.12
     haze
    1.05
     clouds
    1.01
     fog
    0.98
     CLOUD
    0.98
     Haze
    0.95
    Clouds
    0.92
     Fog
    0.91
    clouds
    0.91
    Misty
    0.90
    Activations Density 0.284%

    No Known Activations