© 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. 16-GEMMASCOPE-RES-16K
    11. 6916
    Prev
    Next
    INDEX
    Explanations

    keywords related to eCommerce platforms and shopping guides

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    choices or decisions

    np_acts-logits-general · gemini-2.0-flash

    choosing or selecting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.85
    expandindo
    -0.68
    DotNetBar
    -0.62
     SqlCommand
    -0.59
    baomidou
    -0.57
    extAlignment
    -0.57
    脚注の使い方
    -0.55
    ồm
    -0.54
    +:+
    -0.53
    Parcelize
    -0.52
    POSITIVE LOGITS
     selecting
    1.15
     Selecting
    1.10
    Selecting
    1.08
    Choosing
    1.07
     choosing
    1.06
     Choosing
    1.05
     selection
    1.00
    choosing
    0.94
     Selection
    0.91
     evaluating
    0.85
    Activations Density 0.372%

    No Known Activations