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. 3-GEMMASCOPE-RES-16K
    6. 11177
    Prev
    Next
    INDEX
    Explanations

    structured elements of a web document, such as HTML tags and attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.63
    Fisch
    -0.59
     Withers
    -0.57
     Roskov
    -0.56
    siyon
    -0.55
    ishness
    -0.54
    IRL
    -0.53
    ണ്ട
    -0.53
    Ekster
    -0.53
     otomatig
    -0.52
    POSITIVE LOGITS
    存于互联网档案馆
    0.79
    }")]
    0.78
    ViewFeatures
    0.74
    }]);
    0.72
    )]);
    0.70
    )_/¯
    0.70
    <>());
    0.68
    }});
    0.66
    }));
    0.66
    "]))
    0.66
    Activations Density 0.083%

    No Known Activations