© 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. 41-GEMMASCOPE-RES-16K
    11. 6822
    Prev
    Next
    INDEX
    Explanations

    technical terminologies and procedures related to automotive gear shifting systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageTagHelper
    -0.53
    ftagPool
    -0.46
     getan
    -0.44
    PYX
    -0.39
    HasAnnotation
    -0.39
    кнуть
    -0.38
    LabelTagHelper
    -0.36
     díl
    -0.36
    ITERIA
    -0.36
     Comissão
    -0.35
    POSITIVE LOGITS
     mode
    3.58
     Mode
    3.06
    mode
    3.00
    Mode
    2.86
     MODE
    2.69
     modes
    2.66
    モード
    2.58
    MODE
    2.48
    模式
    2.33
     Modes
    2.28
    Activations Density 0.804%

    No Known Activations