© 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. 34-GEMMASCOPE-RES-16K
    6. 11191
    Prev
    Next
    INDEX
    Explanations

    references to specific queries or identifiers related to data or information processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    原始内容存档于
    -0.54
     فريبيس
    -0.50
    Архівовано
    -0.49
    TargetException
    -0.49
    Derbyniad
    -0.49
     оригіналу
    -0.48
    ChildScrollView
    -0.46
     AssemblyCulture
    -0.44
    InjectAttribute
    -0.42
    datei
    -0.41
    POSITIVE LOGITS
     Q
    0.58
    riceps
    0.47
    tionnaire
    0.43
     q
    0.42
     literally
    0.41
     Tarantino
    0.41
     Qu
    0.39
    싶
    0.39
     sebou
    0.38
    fassung
    0.38
    Activations Density 0.633%

    No Known Activations