© 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. 2-GEMMASCOPE-RES-16K
    11. 14839
    Prev
    Next
    INDEX
    Explanations

    references to Android Bundles and related data structures

    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
     IFC
    -0.59
    Література
    -0.56
    ſelf
    -0.55
     tarts
    -0.55
    udere
    -0.54
     ***!
    -0.54
     Perfon
    -0.54
    AndView
    -0.53
     Kluwer
    -0.52
     Şi
    -0.51
    POSITIVE LOGITS
     Nations
    0.79
     AttributeSet
    0.76
    igshid
    0.72
     treaty
    0.71
    paksa
    0.69
    Nations
    0.68
     Völ
    0.66
     convention
    0.66
    ubarak
    0.64
    Bundle
    0.63
    Activations Density 0.043%

    No Known Activations