© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 15337
    Prev
    Next
    INDEX
    Explanations

    references to concepts of history and memory, particularly relating to the past

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.75
    AndEndTag
    -0.59
     ligiloj
    -0.55
     كومونز
    -0.55
    XmlAccessorType
    -0.53
     ModelRenderer
    -0.53
     surla
    -0.52
    delwed
    -0.52
    новниш
    -0.52
    protoc
    -0.52
    POSITIVE LOGITS
     past
    4.09
    past
    3.44
    Past
    3.20
     Past
    3.19
     PAST
    2.91
    PAST
    2.61
     Vergangenheit
    2.41
     pasado
    2.36
    過去
    2.34
     passato
    2.17
    Activations Density 0.439%

    No Known Activations