© 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. 3807
    Prev
    Next
    INDEX
    Explanations

    terms related to actions and their consequences

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

    Preceding "that," "of," or "which"

    np_acts-logits-general · gemini-2.0-flash

    personal pronouns and references

    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
     يتيمه
    -1.11
     ་་
    -0.95
     Normdatei
    -0.91
     photolibrary
    -0.88
     ―――――
    -0.88
     tfsi
    -0.84
     ――――
    -0.84
     pinulongan
    -0.82
     ―――
    -0.81
     crdi
    -0.80
    POSITIVE LOGITS
     her
    1.47
     his
    1.38
     she
    1.19
     him
    1.16
     he
    1.08
     their
    1.01
     my
    1.00
    his
    0.92
     He
    0.92
     His
    0.87
    Activations Density 3.965%

    No Known Activations