© 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-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12389
    Prev
    Next
    INDEX
    Explanations

    terms related to software components and coding structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ัพท์
    -0.64
     ujednoznacz
    -0.57
    IContainer
    -0.55
     själva
    -0.53
    EndInit
    -0.53
    romycin
    -0.51
     primaire
    -0.50
    setResult
    -0.50
    Sklici
    -0.48
     salu
    -0.47
    POSITIVE LOGITS
    Component
    1.22
     Component
    1.03
    component
    0.84
     component
    0.80
     COMPONENT
    0.72
    getComponent
    0.72
    createComponent
    0.72
     LoginComponent
    0.71
     useStyles
    0.70
     HomeComponent
    0.69
    Activations Density 0.030%

    No Known Activations