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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 5041
    Prev
    Next
    INDEX
    Explanations

    structured data and objects in programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AutoScale
    -0.76
    ClientSize
    -0.73
     defaultstate
    -0.71
    StoryboardSegue
    -0.65
    IVEREF
    -0.64
    Portály
    -0.64
     Baillargeon
    -0.59
    PreferredItem
    -0.56
    glEnd
    -0.56
     JpaRepository
    -0.55
    POSITIVE LOGITS
    endphp
    1.07
    帖最后由
    0.82
    ])[
    0.70
    日閲覧
    0.67
     摩
    0.66
    UserScript
    0.66
    writerow
    0.65
    ματο
    0.64
    IBOutlet
    0.64
    原始内容存档于
    0.64
    Activations Density 0.056%

    No Known Activations