© 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. 8550
    Prev
    Next
    INDEX
    Explanations

    items related to data management and security within documents

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

    Prepositions and German words

    np_acts-logits-general · gemini-2.0-flash

    Funktionen, Schutz, Lösungen, cycle, Lazy, Ricky

    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
    endphp
    -1.00
     estekak
    -0.98
     itſelf
    -0.92
    Viitteet
    -0.88
    resaid
    -0.88
     Efq
    -0.88
    verständlich
    -0.85
    HomeAsUpEnabled
    -0.83
     }}$}
    -0.83
     becauſe
    -0.82
    POSITIVE LOGITS
     des
    0.79
     von
    0.59
     der
    0.53
     zur
    0.51
     của
    0.50
     zum
    0.47
     vom
    0.46
    ,
    0.46
     mit
    0.45
    vi
    0.45
    Activations Density 0.032%

    No Known Activations