© 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. 33-GEMMASCOPE-RES-16K
    11. 11058
    Prev
    Next
    INDEX
    Explanations

    phrases related to information gathering and sharing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueGeneration
    -0.49
    runApp
    -0.46
    SerializeField
    -0.44
    CascadeType
    -0.44
     kaynağından
    -0.43
    Tembelea
    -0.43
    DoubleQuotes
    -0.42
    endphp
    -0.42
    AddTagHelper
    -0.40
    مراجع
    -0.40
    POSITIVE LOGITS
     about
    3.31
    about
    2.28
    About
    2.11
     About
    2.05
     ABOUT
    2.03
     tentang
    1.98
     tungkol
    1.77
     apie
    1.66
    ABOUT
    1.54
    關於
    1.52
    Activations Density 0.809%

    No Known Activations