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. 16-GEMMASCOPE-RES-16K
    6. 14978
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and functions involving dimensions and variables

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

    Mathematical or numerical expressions

    np_acts-logits-general · gemini-2.0-flash

    waitpixels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    />";
    -0.75
    }>;
    -0.74
    }';
    -0.74
    ]';
    -0.71
     houſe
    -0.71
    ,:);
    -0.70
    )';
    -0.69
    >");
    
    -0.66
    Chham
    -0.65
    }');
    -0.65
    POSITIVE LOGITS
     amount
    0.85
     times
    0.65
     cantidad
    0.65
     number
    0.64
    amount
    0.57
     bezeichneter
    0.55
     kadar
    0.52
    th
    0.51
    dean
    0.50
    مین
    0.49
    Activations Density 1.527%

    No Known Activations