© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 5492
    Prev
    Next
    INDEX
    Explanations

    HTML element attributes and classes related to font icons

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

    "fa" or "glyphicon" HTML/CSS class names

    np_acts-logits-general · gemini-2.0-flash

    font awesome icons

    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
    RenderAtEndOf
    -1.08
     propOrder
    -0.96
    :✨
    -0.93
    +#+#
    -0.91
    PerformLayout
    -0.91
    Personendaten
    -0.90
    WriteBarrier
    -0.89
    })));
    -0.89
    Diwedd
    -0.88
    rrggbb
    -0.87
    POSITIVE LOGITS
     fa
    0.97
     Fa
    0.87
    Fa
    0.69
    fa
    0.68
    fortawesome
    0.55
     Faulkner
    0.52
     day
    0.50
     FA
    0.50
    afa
    0.48
    FA
    0.48
    Activations Density 0.026%

    No Known Activations