© 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. 19-GEMMASCOPE-RES-16K
    11. 1732
    Prev
    Next
    INDEX
    Explanations

    terms related to permissions and regulations regarding the use of software and commercial products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reet
    -0.47
     :(
    -0.46
    რი
    -0.42
     SwiftUI
    -0.41
    akah
    -0.41
    ej
    -0.41
     constantemente
    -0.38
    ord
    -0.38
    Failed
    -0.38
    aka
    -0.37
    POSITIVE LOGITS
     شرط
    1.23
     condition
    1.18
     proviso
    1.18
    只要
    1.15
    ただし
    1.13
     asal
    1.11
     solange
    1.10
     بشر
    1.09
    condition
    1.08
     caveat
    1.06
    Activations Density 0.540%

    No Known Activations