© 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. 18-GEMMASCOPE-RES-16K
    11. 4034
    Prev
    Next
    INDEX
    Explanations

    terms related to possession and obtaining

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

    Follows "has," "had," or "got"

    np_acts-logits-general · gemini-2.0-flash

    phrases with "has" or "got"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    initComponents
    -0.58
    يكب
    -0.56
    droj
    -0.56
     myſelf
    -0.54
    }}]{
    -0.53
     plagioclase
    -0.52
    viewWillAppear
    -0.52
    onnaissance
    -0.51
     NCERT
    -0.51
     poffible
    -0.50
    POSITIVE LOGITS
     nothing
    0.81
     them
    0.81
     everyone
    0.75
     everything
    0.71
     everybody
    0.70
     EVERYTHING
    0.68
     plenty
    0.65
     something
    0.64
     NOTHING
    0.63
     فريبيس
    0.62
    Activations Density 0.169%

    No Known Activations