Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 770
    Prev
    Next
    INDEX
    Explanations

    references to musicians and their roles in a band

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

    Acoustic guitar and songwriting

    np_acts-logits-general · gemini-2.0-flash

    acoustic guitar and songwriting

    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
    APORE
    -0.71
    amenti
    -0.56
    oneofs
    -0.56
    RenderAtEndOf
    -0.55
     مشين
    -0.53
     Mosley
    -0.52
    InnerText
    -0.51
     emploi
    -0.50
     Chlorine
    -0.50
    AMENTO
    -0.50
    POSITIVE LOGITS
     guitar
    1.19
     songwriting
    1.14
     songwriter
    1.08
     strum
    1.05
     acoustic
    1.03
     guitarra
    1.02
     guitars
    1.02
    guitar
    0.99
     Guitar
    0.94
     songs
    0.92
    Activations Density 0.099%

    No Known Activations