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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 9481
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations related to statistical mechanics or stochastic processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hope
    -0.38
     support
    -0.32
     welcome
    -0.30
     경
    -0.28
    hope
    -0.28
     HOPE
    -0.28
     host
    -0.27
     human
    -0.27
     part
    -0.27
     local
    -0.25
    POSITIVE LOGITS
    ParallelGroup
    0.74
    期刊论文
    0.69
    ſammen
    0.68
     queſta
    0.68
     jadx
    0.67
    bootstrapcdn
    0.65
    ThroughAttribute
    0.64
    )²
    0.62
     queſto
    0.62
    OGND
    0.61
    Activations Density 1.256%

    No Known Activations