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. 15-GEMMASCOPE-RES-16K
    6. 2890
    Prev
    Next
    INDEX
    Explanations

    aspects of trade-offs related to costs, benefits, and risks

    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
     ogóle
    -0.56
    IActionResult
    -0.47
    TagHelper
    -0.47
    buc
    -0.47
    lotz
    -0.45
    nung
    -0.44
    定
    -0.43
    inton
    -0.43
    InjectMocks
    -0.42
     naturally
    -0.42
    POSITIVE LOGITS
     sacrifices
    0.74
     Sacrific
    0.73
     sacrifice
    0.71
     sacrificing
    0.70
     שוליים
    0.66
    sacrifice
    0.65
     TimeUnit
    0.63
     sacrific
    0.63
     sacrificio
    0.63
     ради
    0.61
    Activations Density 0.333%

    No Known Activations