© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5813
    Prev
    Next
    INDEX
    Explanations

    references to customization and bespoke creations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -1.13
     MessageBoxIcon
    -1.05
    ELTS
    -0.96
     GenerationType
    -0.95
    SpringBootTest
    -0.93
     kasarigan
    -0.93
     createSlice
    -0.90
    ResumeLayout
    -0.90
    AnchorStyles
    -0.88
    DockStyle
    -0.87
    POSITIVE LOGITS
     custom
    3.16
     Custom
    3.01
    custom
    2.92
    Custom
    2.83
     CUSTOM
    2.62
    CUSTOM
    2.42
     customized
    2.19
     customised
    1.98
    setCustom
    1.95
     customs
    1.86
    Activations Density 0.057%

    No Known Activations