© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 3706
    Prev
    Next
    INDEX
    Explanations

    words indicating potential or capability

    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
    WireFormat
    -0.58
     resultCode
    -0.56
     Dominus
    -0.49
    adillas
    -0.49
     dago
    -0.47
    Morris
    -0.46
     okhttp
    -0.45
    fromnode
    -0.45
     inoxid
    -0.44
     Schia
    -0.44
    POSITIVE LOGITS
     ExecuteAsync
    0.71
     possível
    0.65
     GetEnumerator
    0.64
    ])):
    0.62
     possible
    0.60
    StoreMessageInfo
    0.59
     Potenti
    0.58
    possible
    0.57
    Possible
    0.57
     Possible
    0.57
    Activations Density 0.261%

    No Known Activations