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. 20-GEMMASCOPE-RES-16K
    6. 11116
    Prev
    Next
    INDEX
    Explanations

    information related to historical figures and events

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

    Years in the 1990s

    np_acts-logits-general · gemini-2.0-flash

    biographical details and dates

    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
    "]();
    -0.53
    alai
    -0.52
    ators
    -0.47
    ()">
    -0.47
    '])
    
    -0.46
    '}>
    -0.46
     };
    
    -0.46
    "];
    
    -0.45
    lioni
    -0.45
    }]
    
    -0.45
    POSITIVE LOGITS
     Wicidata
    0.75
     esternos
    0.70
     الرياضيه
    0.69
    MigrationBuilder
    0.69
    ::_('
    0.67
    ंदीखरीदारी
    0.65
    oa̍t
    0.65
     Мексичка
    0.62
     Administrativna
    0.61
    SBATCH
    0.61
    Activations Density 0.078%

    No Known Activations