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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 3042
    Prev
    Next
    INDEX
    Explanations

    terms related to digital technology and information management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/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.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bulu
    -0.37
     Verhält
    -0.34
     rozs
    -0.34
     görüntüleri
    -0.33
     dég
    -0.32
     företag
    -0.31
     colgantes
    -0.31
     segi
    -0.31
     near
    -0.31
     prie
    -0.31
    POSITIVE LOGITS
     stack
    0.74
     ecosystems
    0.70
     solutions
    0.70
     ujednoznacz
    0.68
     ecosystem
    0.66
     Ecosystem
    0.65
     architectures
    0.65
     acceleration
    0.65
     Maturity
    0.65
     solution
    0.64
    Activations Density 0.501%

    No Known Activations