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. 18-GEMMASCOPE-RES-16K
    6. 8572
    Prev
    Next
    INDEX
    Explanations

    mentions of the Google brand and its associated services

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

    Follows the word "Google"

    np_acts-logits-general · gemini-2.0-flash

    google products and services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #######
    -0.67
    Tikang
    -0.64
    }*/
    
    -0.61
    §
    -0.61
     Pardo
    -0.57
    <h5>
    -0.56
     Pristupljeno
    -0.56
    ❋
    -0.55
    }$)
    -0.55
     kasarigan
    -0.54
    POSITIVE LOGITS
     Google
    1.29
     GOOGLE
    1.18
     google
    1.17
    Google
    1.17
    GoogleMap
    1.03
    GOOGLE
    1.03
     googled
    1.03
    google
    1.02
    goog
    1.00
     Chrome
    0.94
    Activations Density 0.061%

    No Known Activations