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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 4665
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and expressions, particularly related to structures and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NUMX
    -0.88
     Arb
    -0.83
    corazón
    -0.82
    SerializedName
    -0.81
    Carla
    -0.81
    خواندن
    -0.80
    essayer
    -0.78
     Carla
    -0.77
    fontsize
    -0.77
    mainwindow
    -0.77
    POSITIVE LOGITS
    ↵↵↵↵
    0.89
     )
    0.87
     }
    0.86
     Sosa
    0.85
    ↵↵↵
    0.78
     ]
    0.77
     ):
    0.75
    ogh
    0.75
     );
    0.73
     </
    0.72
    Activations Density 0.180%

    No Known Activations