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. 12-GEMMASCOPE-RES-16K
    6. 6357
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the concept of "of" and its occurrences in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     riuscito
    -0.56
     etme
    -0.53
     îna
    -0.52
    SequentialGroup
    -0.52
     etmeye
    -0.52
    Elijah
    -0.50
     czę
    -0.50
    ออก
    -0.49
     Stockholm
    -0.49
     दिल्ली
    -0.48
    POSITIVE LOGITS
    Portale
    0.83
    ########.
    0.80
    ]='\
    0.73
    Portail
    0.72
    !(:
    0.69
     للمعارف
    0.68
     betweenstory
    0.68
    httphttps
    0.66
    onViewCreated
    0.65
    værende
    0.63
    Activations Density 0.651%

    No Known Activations