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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3731
    Prev
    Next
    INDEX
    Explanations

    the concept of freshness, particularly in food or ingredients

    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
     "..\..\..\
    -0.82
    complexContent
    -0.82
     Leggings
    -0.78
     baseman
    -0.76
     Walkover
    -0.74
     iArr
    -0.73
     кӀ
    -0.72
     >=",
    -0.72
     Organiser
    -0.69
     onOptions
    -0.69
    POSITIVE LOGITS
     fresh
    3.52
    fresh
    3.36
    Fresh
    3.31
     Fresh
    3.31
     FRESH
    3.08
    FRESH
    2.70
     fresher
    2.34
     freshest
    2.32
     freshness
    2.31
     frische
    2.04
    Activations Density 0.039%

    No Known Activations