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. 2-GEMMASCOPE-RES-16K
    6. 4904
    Prev
    Next
    INDEX
    Explanations

    words or phrases that indicate a sense of remaining quantity or leftover items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -1.13
    tagHelperRunner
    -0.89
     BorderRadius
    -0.86
     SwiftUI
    -0.82
     RequestMethod
    -0.82
     مرئيه
    -0.81
     للمعارف
    -0.80
    NewUrlParser
    -0.78
    WebVitals
    -0.76
    EDEFAULT
    -0.75
    POSITIVE LOGITS
     remaining
    1.93
     Remaining
    1.78
    Remaining
    1.68
    remaining
    1.61
     restantes
    1.13
    maining
    1.06
     surviving
    1.06
    剩余
    0.96
     остав
    0.93
    剩下的
    0.92
    Activations Density 0.152%

    No Known Activations