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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 3190
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "fixed" 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 @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SBATCH
    -0.84
    
    -0.84
     שוליים
    -0.83
    InSection
    -0.80
    tagHelperRunner
    -0.78
    ItemBackground
    -0.75
    يكب
    -0.67
    RectangleBorder
    -0.66
    FieldDescriptor
    -0.66
     GetComponent
    -0.66
    POSITIVE LOGITS
     fixed
    3.69
     Fixed
    3.48
    Fixed
    3.45
    fixed
    3.38
     FIXED
    3.23
    FIXED
    2.87
     fix
    2.68
     Fix
    2.58
     fixe
    2.56
    Fix
    2.51
    Activations Density 0.088%

    No Known Activations