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-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 109666
    Prev
    Next
    INDEX
    Explanations

    codes or definitions related to function flags in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.69
    exitRule
    -0.63
    rrggbb
    -0.63
    +#+#
    -0.62
    verwijspagina
    -0.55
    principalTable
    -0.54
    enteric
    -0.51
    lichung
    -0.51
     disambiguazione
    -0.50
    ⤹
    -0.50
    POSITIVE LOGITS
     smtplib
    0.45
    /*
    0.42
    nativeElement
    0.38
     initComponents
    0.38
    });
    
    
    0.36
    }>;
    0.35
     requestCode
    0.34
     />);
    0.34
    )];
    
    0.32
     skå
    0.32
    Activations Density 0.003%

    No Known Activations