© 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. 13848
    Prev
    Next
    INDEX
    Explanations

    references to "Star" or "stars" in various contexts

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

    "Star" followed by "Trek" or "Wars"

    np_acts-logits-general · gemini-2.0-flash

    Star Trek, Star Wars

    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
    //
    -0.73
     Obrador
    -0.73
    PoolSize
    -0.57
    }],
    -0.54
    хьтан
    -0.54
    }));
    -0.52
    jne
    -0.52
     Alors
    -0.51
    ➟
    -0.51
     /\.(
    -0.51
    POSITIVE LOGITS
     Star
    1.25
     Stars
    1.18
     STAR
    1.16
     star
    1.14
     stars
    1.13
    Star
    1.04
    Stars
    1.04
    STAR
    0.97
    star
    0.94
    stars
    0.94
    Activations Density 0.166%

    No Known Activations