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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 12127
    Prev
    Next
    INDEX
    Explanations

    terms related to slots in gaming and machines

    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
    ])));
    -0.99
    '])){
    
    -0.97
    NUMX
    -0.96
    ]';
    -0.96
    "])){
    -0.95
     inoxydable
    -0.95
    creens
    -0.94
    quakes
    -0.94
     Kuri
    -0.94
     pleaſure
    -0.92
    POSITIVE LOGITS
     slot
    3.31
     Slot
    3.08
     slots
    2.97
    Slot
    2.85
    slot
    2.83
     Slots
    2.81
     SLOT
    2.46
    Slots
    2.42
    slots
    2.33
    SLOT
    2.25
    Activations Density 0.049%

    No Known Activations