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. 5-GEMMASCOPE-RES-16K
    6. 1481
    Prev
    Next
    INDEX
    Explanations

    blocks of code or structured data elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InputBorder
    -1.11
    EndContext
    -1.09
     BoxDecoration
    -1.01
    ConstraintMaker
    -0.97
    ArgsConstructor
    -0.95
     تضيفلها
    -0.92
    WaitGroup
    -0.90
     CreateTagHelper
    -0.89
    帖最后由
    -0.88
    styleType
    -0.84
    POSITIVE LOGITS
    ↵↵
    0.80
    __':
    
    0.73
     }}>
    0.62
    }}],
    0.62
    )}>
    0.61
    }}>
    0.61
    '}}>
    0.60
    __":
    
    0.60
    __':
    0.60
    []){
    0.60
    Activations Density 0.065%

    No Known Activations