© 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-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 10783
    Prev
    Next
    INDEX
    Explanations

    references to components, performance, and combinations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnsafeEnabled
    -0.67
    SBATCH
    -0.64
    Зноскі
    -0.59
     PhpStorm
    -0.57
    MessageOf
    -0.56
    таратура
    -0.55
    Ծանոթ
    -0.55
    הערות
    -0.54
    ագրություններ
    -0.53
     getRule
    -0.52
    POSITIVE LOGITS
    mbic
    0.57
     sockaddr
    0.51
    phite
    0.51
    HostException
    0.51
    züglich
    0.51
     alike
    0.50
     ​​
    0.49
    RefNanny
    0.48
    theim
    0.48
    ads
    0.47
    Activations Density 0.435%

    No Known Activations