© 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. 8912
    Prev
    Next
    INDEX
    Explanations

    terms related to magnetic fields and their manipulation in scientific contexts

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

    magnetic or electric fields

    np_acts-logits-general · gemini-2.0-flash

    electric and magnetic fields

    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
    iredo
    -0.54
    ínsula
    -0.46
    ylinder
    -0.43
    Soorten
    -0.41
    alamus
    -0.41
     INSEE
    -0.41
    LessThan
    -0.41
    RefreshToken
    -0.41
    uszcz
    -0.40
    潤
    -0.39
    POSITIVE LOGITS
     gravitational
    0.85
     gravity
    0.85
     magnetic
    0.85
    expandindo
    0.84
     force
    0.82
     fields
    0.82
     field
    0.79
     gradient
    0.77
     forces
    0.76
     gradients
    0.75
    Activations Density 0.597%

    No Known Activations