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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 1404
    Prev
    Next
    INDEX
    Explanations

    percentage values or formats related to data

    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
    )";
    
    -0.99
    دانشنامهٔ
    -0.85
    ."]
    -0.78
    )");
    
    -0.75
    లాలు
    -0.72
    "])
    
    -0.69
    ]";
    -0.69
     doubtnut
    -0.69
    FunctionFlags
    -0.69
    "]();
    -0.67
    POSITIVE LOGITS
     %
    1.39
    ="%
    1.28
    ("%
    1.18
     \%
    1.15
    ('%
    1.14
    ,"%
    1.14
     "%
    1.08
    ='%
    1.07
    =%
    1.06
    :%
    1.06
    Activations Density 0.098%

    No Known Activations