© 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. 22-GEMMASCOPE-RES-16K
    11. 14942
    Prev
    Next
    INDEX
    Explanations

    terms and names associated with technology and product features in a digital context

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

    or fragments preceding trademark/copyright symbols

    np_acts-logits-general · gemini-2.0-flash

    registered trademark symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    — 
    -0.86
    SourceChecksum
    -0.84
    …]
    -0.78
    /−
    -0.77
    CloseOperation
    -0.76
    mybatisplus
    -0.76
    )​
    -0.75
    KURZBESCHREIBUNG
    -0.74
    .)}
    -0.74
    ChildScrollView
    -0.72
    POSITIVE LOGITS
    ®
    2.64
    ™
    2.37
    ®,
    2.08
    ®.
    2.05
     ®
    1.96
    TM
    1.93
     ™
    1.88
    ™,
    1.84
    ™.
    1.84
    ®:
    1.81
    Activations Density 0.659%

    No Known Activations