© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5840
    Prev
    Next
    INDEX
    Explanations

    instances of charset-related specifications in coding contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ंदीखरीदारी
    -0.65
    usercontent
    -0.64
    ClickListener
    -0.62
    enumi
    -0.62
    ’?
    -0.60
     Quir
    -0.60
     Humphreys
    -0.58
     సౌకర్య
    -0.56
    ?—
    -0.56
    nasium
    -0.55
    POSITIVE LOGITS
     charset
    1.06
    mstyle
    0.94
    </thead>
    0.91
    Errorf
    0.90
    ActionListener
    0.85
     Retrieved
    0.76
    FromArgb
    0.75
    ContentAsync
    0.70
     CreateTagHelper
    0.70
    WEBPACK
    0.68
    Activations Density 0.007%

    No Known Activations