© 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. 6686
    Prev
    Next
    INDEX
    Explanations

    elements related to statements, documents, and formal writings

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

    Follows nouns indicating formal announcements or declarations

    np_acts-logits-general · gemini-2.0-flash

    formal declarations with subsequent actions

    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
    Analyzing
    -0.94
     Theſe
    -0.93
     Representing
    -0.91
     Jefus
    -0.90
     houſe
    -0.89
     greateſt
    -0.87
     Diſ
    -0.85
     ſch
    -0.85
     Analyzing
    -0.85
     poffible
    -0.85
    POSITIVE LOGITS
     with
    0.60
    ,
    0.56
     and
    0.54
     remaining
    0.54
     in
    0.53
     ISNI
    0.48
     (
    0.46
     at
    0.45
     as
    0.45
    ständig
    0.44
    Activations Density 0.387%

    No Known Activations