Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-GEMMASCOPE-RES-16K
    6. 3134
    Prev
    Next
    INDEX
    Explanations

    specific numeric or formatting patterns indicative of technical specifications or code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :].
    -0.97
    )"),
    -0.91
    )");
    
    -0.89
    :]:
    -0.89
     referenties
    -0.87
    ."],
    -0.86
     باخ
    -0.86
    :],
    -0.85
     himo
    -0.82
    ']):
    -0.82
    POSITIVE LOGITS
    0
    1.58
     zero
    0.94
    zero
    0.90
     Zero
    0.88
     Zer
    0.85
     صفر
    0.84
    Zero
    0.84
     zéro
    0.82
     ZERO
    0.79
     cero
    0.77
    Activations Density 0.921%

    No Known Activations