© 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. 2539
    Prev
    Next
    INDEX
    Explanations

    terms related to improvements in efficiency or performance metrics

    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
    SPATH
    -0.55
     custos
    -0.50
    BeforeMethod
    -0.46
     costs
    -0.46
     Costs
    -0.46
     fortsetter
    -0.45
     potrivit
    -0.44
    /**
    -0.43
     adieu
    -0.42
     costes
    -0.42
    POSITIVE LOGITS
     насељу
    0.74
     disponibilités
    0.72
    MessageOf
    0.72
     productivity
    0.69
    IsMutable
    0.69
     ]);
    0.67
    AddTagHelper
    0.67
    GIVEREF
    0.66
    ParallelGroup
    0.64
    WriteAttribute
    0.64
    Activations Density 0.409%

    No Known Activations