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. 5-GEMMASCOPE-RES-16K
    6. 8679
    Prev
    Next
    INDEX
    Explanations

    various forms of whitespace or invisible characters in the text

    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
     onCreateView
    -0.76
     ..."
    -0.75
    yarnpkg
    -0.74
     JTextField
    -0.73
     createStore
    -0.72
    Pozri
    -0.72
     Bona
    -0.72
     
    -0.69
    .".
    -0.68
     FetchType
    -0.68
    POSITIVE LOGITS
    ​
    2.12
     ​
    1.94
    )​
    1.88
    .​
    1.66
    ,​
    1.56
    $​
    1.48
    ​.
    1.44
    :​
    1.44
    ​,
    1.43
    ​​
    1.42
    Activations Density 0.382%

    No Known Activations