© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 9338
    Prev
    Next
    INDEX
    Explanations

    references to Broadway productions and their creators

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

    "musical" and "play"

    np_acts-logits-general · gemini-2.0-flash

    Broadway musicals

    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
     '\\;'
    -0.59
    BeginContext
    -0.57
    UnknownFieldSet
    -0.56
    aimerais
    -0.54
    ptonshire
    -0.53
    })));
    -0.52
    ThroughAttribute
    -0.52
    XDECREF
    -0.52
     فريبيس
    -0.51
    pendenti
    -0.51
    POSITIVE LOGITS
     musicals
    1.22
     musical
    1.10
     Broadway
    1.07
     Musical
    1.03
    musical
    0.99
     MUSICAL
    0.93
    Musical
    0.92
    Broadway
    0.90
     musicales
    0.89
     broadway
    0.86
    Activations Density 0.058%

    No Known Activations