© 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. 2-GEMMASCOPE-RES-16K
    6. 3926
    Prev
    Next
    INDEX
    Explanations

    terms and code related to data repositories and database interactions in Spring framework applications

    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
     المعيارى
    -0.75
     NSCoder
    -0.75
     فريبيس
    -0.74
    ftagPool
    -0.71
    WithIdentifier
    -0.68
    EndInit
    -0.66
    IndentedString
    -0.65
     createSlice
    -0.63
    onAttach
    -0.63
    RenderAtEndOf
    -0.63
    POSITIVE LOGITS
     Spo
    0.62
    spo
    0.61
     apo
    0.60
    Spo
    0.58
     spo
    0.55
    Diplom
    0.51
     Ass
    0.51
     ASS
    0.50
    chett
    0.50
    Ин
    0.50
    Activations Density 4.422%

    No Known Activations