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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 1188
    Prev
    Next
    INDEX
    Explanations

    the presence of structured or formatted scientific data and metadata

    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
    ugeot
    -0.94
    Rhestr
    -0.82
     FormsModule
    -0.81
    mybatisplus
    -0.77
    LLocation
    -0.74
    iffance
    -0.74
    ruptedException
    -0.73
     $_"
    -0.72
    ázaro
    -0.71
     BoxFit
    -0.70
    POSITIVE LOGITS
    ↵↵
    1.97
    ↵↵↵
    1.47
    ↵↵↵↵
    1.38
    <eos>
    1.35
    ↵
    1.35
    ↵↵↵↵↵
    1.34
    <h2>
    1.27
    ↵↵↵↵↵↵
    1.23
    <blockquote>
    1.14
    [toxicity=0]
    1.13
    Activations Density 0.000%

    No Known Activations