© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13594
    Prev
    Next
    INDEX
    Explanations

    phrases related to the fabrication or composition of objects and materials

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

    "Made of" or variants

    np_acts-logits-general · gemini-2.0-flash

    made of or with

    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
    TestBed
    -0.60
    Personensuche
    -0.58
     مشين
    -0.57
    keyColumn
    -0.57
     Biôgrafia
    -0.57
    XmlAttribute
    -0.56
    casian
    -0.56
     &___
    -0.54
    Datuak
    -0.53
     للاسماء
    -0.53
    POSITIVE LOGITS
     made
    1.91
    made
    1.55
     Made
    1.51
    Made
    1.47
     terbuat
    1.39
     constructed
    1.36
     MADE
    1.33
     gemaakt
    1.30
     crafted
    1.29
     hecha
    1.25
    Activations Density 0.244%

    No Known Activations