© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 7918
    Prev
    Next
    INDEX
    Explanations

    variations of the word "so" in different contexts

    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
    featureID
    -0.47
    脚注の使い方
    -0.45
    GEBURTS
    -0.45
     kasarigan
    -0.45
    complexContent
    -0.44
    Архівовано
    -0.40
     insuffisamment
    -0.39
    CppCodeGen
    -0.38
    findpost
    -0.38
    IVEREF
    -0.38
    POSITIVE LOGITS
    So
    0.48
     far
    0.47
    createCanvas
    0.46
     So
    0.46
     EconPapers
    0.45
    WebElementEntity
    0.42
    called
    0.42
    laces
    0.42
    lider
    0.42
    jour
    0.42
    Activations Density 0.163%

    No Known Activations