© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 1283
    Prev
    Next
    INDEX
    Explanations

    themes related to contrasting worlds or experiences

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

    "world" or "worlds"

    np_acts-logits-general · gemini-2.0-flash

    worlds, their, two, both

    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
     long
    -0.43
     histórica
    -0.41
    ngths
    -0.40
     tulang
    -0.40
     stood
    -0.39
     Long
    -0.39
     STO
    -0.39
     put
    -0.39
     standing
    -0.39
    ğa
    -0.38
    POSITIVE LOGITS
     world
    1.86
     worlds
    1.82
    world
    1.65
     mundo
    1.53
     universe
    1.46
    worlds
    1.45
    WORLD
    1.33
     WORLD
    1.31
    世界
    1.31
     wereld
    1.27
    Activations Density 0.203%

    No Known Activations