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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 122915
    Prev
    Next
    INDEX
    Explanations

    references to mountains or elevated geographical features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.67
    tagHelperRunner
    -0.56
     aihe
    -0.49
    esModule
    -0.49
     dày
    -0.48
     zitten
    -0.46
     vzduchu
    -0.45
     kijken
    -0.45
    存于互联网档案馆
    -0.45
    tidumbre
    -0.45
    POSITIVE LOGITS
    })).
    0.58
    Portale
    0.56
    ])).
    0.56
    ".$_
    0.56
    }}_{
    0.54
    
    0.53
    ))).
    0.53
    "+
    
    0.51
     Cape
    0.50
     Palazzo
    0.50
    Activations Density 0.047%

    No Known Activations