© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 3236
    Prev
    Next
    INDEX
    Explanations

    attributes associated with UI elements in code

    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
    AsUp
    -0.88
    ChildScrollView
    -0.85
    adpleegd
    -0.85
    PreferredItem
    -0.84
     otomatig
    -0.81
    PerformLayout
    -0.79
    ########.
    -0.79
    expandindo
    -0.77
    windowFixed
    -0.77
    aarrggbb
    -0.77
    POSITIVE LOGITS
    hline
    0.82
     each
    0.56
     otur
    0.54
     lettera
    0.52
     none
    0.51
    ="@+
    0.50
    otel
    0.49
    ißt
    0.49
    <tr>
    0.48
     gebru
    0.45
    Activations Density 0.012%

    No Known Activations