© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 3779
    Prev
    Next
    INDEX
    Explanations

    the frequency and predominance of words related to majority or commonality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    さらに
    -0.47
    WithIdentifier
    -0.43
    InjectMocks
    -0.40
     Swann
    -0.40
    NLS
    -0.38
     further
    -0.38
    onent
    -0.37
     onAnimation
    -0.37
    inander
    -0.36
     potential
    -0.36
    POSITIVE LOGITS
     flesta
    0.99
     maioria
    0.93
     majority
    0.90
     meisten
    0.90
     kebanyakan
    0.89
     plupart
    0.87
    Majority
    0.86
    majority
    0.84
     meeste
    0.83
     fleste
    0.82
    Activations Density 0.449%

    No Known Activations