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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8426
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate agreement or similarity

    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
    )";
    
    -0.87
    )");
    
    -0.87
     ―――――
    -0.83
     propOrder
    -0.76
    "]
    
    -0.74
    ]";
    -0.73
    "]);
    
    -0.73
    "):
    
    -0.71
    "';
    -0.70
    .",
    
    -0.70
    POSITIVE LOGITS
    endphp
    0.74
    ########.
    0.71
    verwijspagina
    0.64
     []:
    0.64
    帖最后由
    0.63
    ,
    0.63
    since
    0.62
     since
    0.59
    ละ
    0.51
     וכל
    0.50
    Activations Density 0.426%

    No Known Activations