© 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. 20-GEMMASCOPE-RES-16K
    11. 8015
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to transformations and rotations

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

    "Turn" or "turned" variations

    np_acts-logits-general · gemini-2.0-flash

    turn and flip

    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
    存于互联网档案馆
    -0.61
    IntoConstraints
    -0.61
    findpost
    -0.55
    loyment
    -0.55
    AndEndTag
    -0.53
    dataclass
    -0.52
    gencies
    -0.51
    tagHelperRunner
    -0.51
    стракт
    -0.50
    jeeling
    -0.50
    POSITIVE LOGITS
     turn
    1.90
    turn
    1.79
     Turn
    1.73
    Turn
    1.71
     turned
    1.68
     turning
    1.68
     TURN
    1.61
     turns
    1.60
     Turning
    1.58
    Turning
    1.53
    Activations Density 0.239%

    No Known Activations