© 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. 18-GEMMASCOPE-RES-16K
    11. 6157
    Prev
    Next
    INDEX
    Explanations

    elements related to magical abilities and technology integration

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

    Magical abilities, powers, and talents

    np_acts-logits-general · gemini-2.0-flash

    magical powers and abilities

    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
    CodedInputStream
    -0.66
     ratification
    -0.60
    ynchronously
    -0.60
    SpringBootTest
    -0.58
    ichord
    -0.56
    OrEmpty
    -0.56
     Sump
    -0.55
     <>",
    -0.55
     stratigraphy
    -0.53
    OrNull
    -0.53
    POSITIVE LOGITS
     powers
    1.40
     abilities
    1.28
     superpowers
    1.20
    powers
    1.14
     superpower
    1.08
     ability
    1.05
     power
    1.01
     Abilities
    1.01
     Powers
    0.98
    能力
    0.96
    Activations Density 0.358%

    No Known Activations