© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 8484
    Prev
    Next
    INDEX
    Explanations

    terms related to third-party involvement and contractual obligations

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

    "Third party" or "other party"

    np_acts-logits-general · gemini-2.0-flash

    third party

    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
    出版年
    -0.59
     ujednoznacz
    -0.52
    enumii
    -0.50
    thâu
    -0.48
    usec
    -0.47
    íncia
    -0.46
    europa
    -0.45
    cahontas
    -0.45
    woordig
    -0.43
     emas
    -0.43
    POSITIVE LOGITS
     party
    3.40
     parties
    3.29
    party
    3.10
    Party
    2.88
     Party
    2.83
    parties
    2.81
     PARTY
    2.80
     Parties
    2.77
    PARTY
    2.63
    Parties
    2.61
    Activations Density 0.399%

    No Known Activations