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. 2-GEMMASCOPE-RES-16K
    6. 1212
    Prev
    Next
    INDEX
    Explanations

    html and XML tags and their structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rüyada
    -0.78
    bership
    -0.73
    Demografia
    -0.65
    ...@
    -0.64
     Spisak
    -0.62
     vnder
    -0.62
    <bos>
    -0.62
     /*#__
    -0.61
     Савезне
    -0.60
     demain
    -0.58
    POSITIVE LOGITS
    DoubleQuotes
    0.85
    __":
    
    0.76
    __':
    
    0.75
     }}$}
    0.72
     }}$
    0.70
    </sub>
    0.69
     }}
    0.69
     }},
    0.68
    MethodManager
    0.67
    󠁿
    0.66
    Activations Density 0.097%

    No Known Activations