© 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. 3-GEMMASCOPE-RES-16K
    11. 9941
    Prev
    Next
    INDEX
    Explanations

    terms related to fixed values, primarily in financial and technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.94
    يكب
    -0.80
    cshtml
    -0.79
    tagHelperRunner
    -0.77
    ruptedException
    -0.75
    SBATCH
    -0.74
     blessé
    -0.74
    seamnă
    -0.74
     desorption
    -0.74
     consultato
    -0.73
    POSITIVE LOGITS
     fixed
    2.90
     Fixed
    2.77
    Fixed
    2.74
    fixed
    2.62
     FIXED
    2.44
    FIXED
    2.25
     fixe
    1.59
    固定
    1.51
     fija
    1.44
     fijo
    1.44
    Activations Density 0.103%

    No Known Activations