© 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. 40-GEMMASCOPE-RES-16K
    6. 1491
    Prev
    Next
    INDEX
    Explanations

    instances of software and technical plugin or application-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTS
    -0.51
    osgi
    -0.48
    WriteTagHelper
    -0.47
    ymce
    -0.47
    XMLSchema
    -0.45
    ClientRect
    -0.45
     aihe
    -0.42
    lwjgl
    -0.42
    SRAM
    -0.42
    WriteAttribute
    -0.41
    POSITIVE LOGITS
     Easy
    0.47
    脚注の使い方
    0.43
    Pyx
    0.42
     Juice
    0.42
     المعيارى
    0.42
     Hyper
    0.41
    "]))
    0.41
     Simple
    0.40
     ivelany
    0.40
     Cute
    0.38
    Activations Density 0.907%

    No Known Activations