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. 21-GEMMASCOPE-RES-16K
    6. 956
    Prev
    Next
    INDEX
    Explanations

    elements related to comparison and contrast

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.64
     Wiktionnaire
    -0.60
    _));
    -0.54
    RuleContext
    -0.53
    რი
    -0.51
     nahilalakip
    -0.51
    ("-");
    -0.50
    )++;
    -0.50
    ]!='
    -0.49
    });*/
    -0.48
    POSITIVE LOGITS
     above
    2.62
    Above
    2.43
     Above
    2.40
    above
    2.38
     ABOVE
    1.99
     most
    1.88
     acima
    1.86
    ABOVE
    1.63
    most
    1.51
     soprattutto
    1.49
    Activations Density 0.208%

    No Known Activations