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. 73558
    Prev
    Next
    INDEX
    Explanations

    numerical data and their manipulations in code

    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
    ])*
    -0.59
    ')}
    -0.57
    \}}
    -0.56
    )))))
    -0.55
    )))),
    -0.54
    /]
    -0.54
    VYMaps
    -0.53
    ]}
    -0.52
    oa̍t
    -0.52
    '))
    
    -0.52
    POSITIVE LOGITS
    Erreferentziak
    0.52
    MessageTagHelper
    0.51
     enfans
    0.48
     présidenti
    0.43
     tutkim
    0.41
     يتيمه
    0.41
     devriez
    0.40
     raiſ
    0.40
     navideño
    0.40
     blessés
    0.39
    Activations Density 0.040%

    No Known Activations