Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 9913
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and operations

    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
    出版年
    -0.53
     atlik
    -0.47
    Kool
    -0.46
    بد
    -0.46
    Fech
    -0.46
    etur
    -0.45
    تفصیلات
    -0.45
    <bos>
    -0.44
    افر
    -0.43
     וב
    -0.42
    POSITIVE LOGITS
    SequentialGroup
    0.85
    )";
    
    0.84
    TagMode
    0.79
    }';
    0.76
    SOUNDBITE
    0.74
    ('');
    
    0.74
    ConstraintMaker
    0.72
    };*/
    0.70
    WriteTagHelper
    0.69
     שוליים
    0.69
    Activations Density 0.768%

    No Known Activations