© 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. 1324
    Prev
    Next
    INDEX
    Explanations

    terms related to liability, managerial functions, and technical adjustments in various contexts

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

    followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    recruiting, defines, supervised, generates

    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
     فريبيس
    -0.79
    SequentialGroup
    -0.67
    HasForeignKey
    -0.63
     ujednoznacz
    -0.61
    !*\
    -0.59
    Хьажоргаш
    -0.58
     linkovi
    -0.57
     يتيمه
    -0.55
    uação
    -0.54
     esternos
    -0.54
    POSITIVE LOGITS
    //</
    0.34
    겸
    0.32
    ⋱
    0.29
     conference
    0.29
     Heiligen
    0.28
     представлены
    0.28
    essentiel
    0.27
     обо
    0.27
    Empereur
    0.27
    AppContext
    0.27
    Activations Density 0.479%

    No Known Activations