© 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. 4-GEMMASCOPE-RES-16K
    11. 16172
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing purpose or justification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Subview
    -0.45
    ствием
    -0.45
     familiar
    -0.44
    acruz
    -0.43
    كويكب
    -0.43
     Dampf
    -0.43
    ENABLE
    -0.43
     aprecia
    -0.43
    致
    -0.42
    Expertise
    -0.42
    POSITIVE LOGITS
     estekak
    1.02
     utafitiHapana
    0.98
     المعيارى
    0.95
     surla
    0.92
     EconPapers
    0.81
     ProtoMessage
    0.79
     تانيه
    0.77
    mybatisplus
    0.76
    TagMode
    0.75
    PerformLayout
    0.74
    Activations Density 0.380%

    No Known Activations