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-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 9679
    Prev
    Next
    INDEX
    Explanations

    references to locations, organizations, and events related to sports and legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مرئيه
    -0.72
    httphttps
    -0.66
    MemoryWarning
    -0.50
     informée
    -0.47
     זו
    -0.47
    béco
    -0.47
     Wicidata
    -0.47
    __":
    -0.47
    MessageOf
    -0.45
    $_['
    -0.45
    POSITIVE LOGITS
     where
    1.96
    where
    1.50
     donde
    1.43
     où
    1.34
     где
    1.20
     waar
    1.17
     Where
    1.14
     gdzie
    1.13
     wherein
    1.13
     hvor
    1.11
    Activations Density 0.558%

    No Known Activations