© 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. 13-GEMMASCOPE-RES-16K
    6. 8039
    Prev
    Next
    INDEX
    Explanations

    instances and discussions related to specific legal cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.32
     ut
    -0.29
     ever
    -0.29
    subpackage
    -0.28
    nessy
    -0.27
    zen
    -0.27
    ttn
    -0.27
     lumin
    -0.25
     Ut
    -0.24
    すぐ
    -0.24
    POSITIVE LOGITS
    modelBuilder
    0.63
     mijne
    0.60
     Diſ
    0.58
     Jefus
    0.58
    QMetaType
    0.56
    __':
    0.56
    avyzd
    0.56
    __":
    
    0.56
    wakili
    0.55
    EndContext
    0.55
    Activations Density 0.581%

    No Known Activations