© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5205
    Prev
    Next
    INDEX
    Explanations

    formal mathematical statements or equations that define relationships and parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical/scientific equations containing "where"

    np_acts-logits-general · gemini-2.0-flash

    defining variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    didReceive
    -0.62
    endphp
    -0.57
     ſche
    -0.57
    Geplaatst
    -0.56
     queſta
    -0.54
    حوالہ
    -0.53
    polation
    -0.52
     myſelf
    -0.52
    PreInfinity
    -0.52
    GOTREF
    -0.51
    POSITIVE LOGITS
     arbejds
    0.38
     detaljer
    0.37
     variables
    0.36
    hæng
    0.36
     details
    0.35
     nhiên
    0.34
    特别
    0.34
     gæ
    0.34
     člověk
    0.33
     Chwiliwch
    0.33
    Activations Density 0.805%

    No Known Activations