© 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. 15-GEMMASCOPE-RES-16K
    6. 3055
    Prev
    Next
    INDEX
    Explanations

    CSS styling properties and their values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    
    -0.86
    AndEndTag
    -0.84
    __":
    
    -0.82
     Baillargeon
    -0.79
    MemoryWarning
    -0.71
    ValueGeneration
    -0.70
    ==""){
    -0.69
    WriteBarrier
    -0.65
    transQ
    -0.64
    ętr
    -0.64
    POSITIVE LOGITS
     medium
    0.59
     Morde
    0.58
    μία
    0.57
     Ibarra
    0.57
    EventListener
    0.54
     Thomson
    0.53
    MEDIUM
    0.53
    MigrationBuilder
    0.52
    MENAFN
    0.51
    raud
    0.50
    Activations Density 0.052%

    No Known Activations