Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 9166
    Prev
    Next
    INDEX
    Explanations

    contextual information regarding entities, relationships, and processes in a narrative or informational text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noastre
    -0.43
    vânt
    -0.38
     săptăm
    -0.38
     règne
    -0.35
     noastră
    -0.35
     seguida
    -0.35
     preocupaciones
    -0.34
     meille
    -0.34
    recated
    -0.34
     trône
    -0.34
    POSITIVE LOGITS
    tagext
    0.68
     subordin
    0.60
    ChildScrollView
    0.59
     subserv
    0.58
     subordinate
    0.57
     Attached
    0.56
     AssemblyCulture
    0.56
    Embeddable
    0.56
     nahilalakip
    0.56
     attached
    0.55
    Activations Density 0.687%

    No Known Activations