© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8229
    Prev
    Next
    INDEX
    Explanations

    references to creative works and their reception

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

    after "has," "will," "that," or similar auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    receiving or attracting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rospy
    -0.61
    AddHtmlAttribute
    -0.59
     betweenstory
    -0.58
    kömm
    -0.57
    كونات
    -0.56
    PreferredItem
    -0.56
    estacks
    -0.56
     Protobuf
    -0.55
    StructEnd
    -0.55
    JKLM
    -0.55
    POSITIVE LOGITS
     attracting
    1.54
     receive
    1.52
     attract
    1.48
     garner
    1.47
     received
    1.46
     receives
    1.46
     receiving
    1.44
     attracts
    1.33
     attracted
    1.25
     Receiving
    1.24
    Activations Density 0.498%

    No Known Activations