© 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. 5-GEMMASCOPE-RES-16K
    6. 6382
    Prev
    Next
    INDEX
    Explanations

    sequences of temporal conjunctions that indicate progression or subsequent actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kids
    -0.56
     nulle
    -0.55
     milliards
    -0.53
     ça
    -0.53
     somethin
    -0.52
     purpoſe
    -0.52
     ihop
    -0.51
     känna
    -0.51
     Partici
    -0.51
    ostante
    -0.51
    POSITIVE LOGITS
    AsUp
    0.94
     nunmehr
    0.80
     now
    0.79
     thereafter
    0.75
    Carriera
    0.72
    énario
    0.71
     subsequently
    0.71
    وأضاف
    0.66
    ormais
    0.66
    Diweddarwch
    0.66
    Activations Density 0.133%

    No Known Activations