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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 10385
    Prev
    Next
    INDEX
    Explanations

    titles and key details of music albums and performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kezés
    -0.55
    readObject
    -0.51
    HtmlAttribute
    -0.48
    JsonInclude
    -0.46
    XmlType
    -0.46
    tagez
    -0.45
     vétérina
    -0.44
    sidemargin
    -0.42
     tromper
    -0.42
     Kakashi
    -0.42
    POSITIVE LOGITS
     music
    2.08
     musically
    1.98
     musicians
    1.96
     musical
    1.92
     songs
    1.90
     Music
    1.86
    music
    1.81
    Music
    1.77
     musician
    1.75
     song
    1.73
    Activations Density 1.780%

    No Known Activations