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 Post
    5. 12-GEMMASCOPE-RES-1M
    6. 495
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    1,048,576
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pauvreté
    -0.52
     skydd
    -0.52
     scelte
    -0.52
     affinch
    -0.52
     indoss
    -0.51
     fatica
    -0.50
     tramonto
    -0.49
    twimg
    -0.48
     Sociales
    -0.47
    وك
    -0.46
    POSITIVE LOGITS
     */;
    0.91
     pinulongan
    0.84
    ()]);
    0.83
     ]
    
    0.81
    ")));
    
    0.81
    ".
    
    0.81
    '))
    
    0.79
    DoubleQuotes
    0.79
    "):
    
    0.79
    "])
    
    0.79
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.