© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 14114
    Prev
    Next
    INDEX
    Explanations

    references to the word "bag" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    starting with "Bog" or "bag"

    np_acts-logits-general · gemini-2.0-flash

    bag or bog variants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portale
    -0.61
    StoryboardSegue
    -0.60
    SpringBoot
    -0.57
    DebuggerNonUser
    -0.57
        
    -0.57
     ild
    -0.57
    <%=
    -0.55
     Utama
    -0.54
    cestershire
    -0.53
    clientWidth
    -0.53
    POSITIVE LOGITS
    bag
    0.85
     bag
    0.83
    Bag
    0.76
     Bog
    0.74
     bags
    0.74
     Bag
    0.72
    BAG
    0.72
    bags
    0.71
     Bags
    0.70
     BAG
    0.68
    Activations Density 0.100%

    No Known Activations