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. 12-GEMMASCOPE-RES-16K
    6. 5160
    Prev
    Next
    INDEX
    Explanations

    references to mathematical or statistical concepts, particularly involving operations or functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     المعيارى
    -0.74
     الحره
    -0.57
    ьаж
    -0.55
    TypedDataSet
    -0.54
     Italijanski
    -0.53
    DataSnapshot
    -0.51
    usepackage
    -0.51
    ionization
    -0.50
    SerializedName
    -0.50
     femenina
    -0.50
    POSITIVE LOGITS
    ")));
    
    0.81
     متعلقه
    0.72
    __":
    
    0.71
    __':
    
    0.70
    }));
    
    0.68
    '));
    
    0.67
    "));
    
    0.66
    SourceChecksum
    0.65
    iecie
    0.65
    Hozzáférés
    0.64
    Activations Density 5.830%

    No Known Activations