© 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. 3847
    Prev
    Next
    INDEX
    Explanations

    sentences expressing actions or conditions related to receiving or obtaining something

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

    Japanese text

    np_acts-logits-general · gemini-2.0-flash

    Japanese and Spanish verbs, English past tense verbs

    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
     Añade
    -0.60
     وين
    -0.57
     spoken
    -0.55
    written
    -0.53
     fazem
    -0.53
     hablan
    -0.53
     juegan
    -0.53
     llegan
    -0.52
     ويت
    -0.52
    poken
    -0.51
    POSITIVE LOGITS
     was
    1.80
     took
    1.77
     went
    1.67
     did
    1.65
     gave
    1.62
     came
    1.55
     didn
    1.48
     became
    1.47
     began
    1.44
    took
    1.42
    Activations Density 0.054%

    No Known Activations