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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15777
    Prev
    Next
    INDEX
    Explanations

    information related to music and songs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.36
     ब्रेकडाउन
    -0.31
     electrico
    -0.30
     vertes
    -0.30
    czaj
    -0.29
    GrantedAuthority
    -0.29
     gangen
    -0.29
     avantage
    -0.29
    tekend
    -0.29
    reszcie
    -0.29
    POSITIVE LOGITS
     soundtrack
    0.64
    DockStyle
    0.61
     overlay
    0.60
     background
    0.58
     banner
    0.56
     collage
    0.56
     edited
    0.53
     slideshow
    0.52
     clips
    0.52
    ilyn
    0.52
    Activations Density 0.186%

    No Known Activations