© 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. 25-GEMMASCOPE-RES-16K
    11. 307
    Prev
    Next
    INDEX
    Explanations

    terms related to data privacy and information handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StructEnd
    -0.81
    DockStyle
    -0.78
    tagHelperRunner
    -0.78
    WebElementEntity
    -0.77
     betweenstory
    -0.70
     ویکی‌پدیا
    -0.70
    providedIn
    -0.69
    ScopeManager
    -0.67
    +#+#
    -0.66
    aarrggbb
    -0.63
    POSITIVE LOGITS
     Personally
    0.95
     sensitive
    0.94
     personally
    0.94
     personal
    0.88
    Personally
    0.83
     Sensitive
    0.70
    personal
    0.66
     private
    0.65
    sensitive
    0.64
     customer
    0.64
    Activations Density 0.377%

    No Known Activations