© 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. 2-GEMMASCOPE-RES-16K
    11. 16216
    Prev
    Next
    INDEX
    Explanations

    terms related to engineering and technical assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -1.07
    ScopeManager
    -1.01
     ivelany
    -0.99
    AnimationsModule
    -0.95
    ContentAsync
    -0.88
    ंदीखरीदारी
    -0.88
     تضيفلها
    -0.86
    SpringRunner
    -0.85
    @[+][
    -0.84
    存于互联网档案馆
    -0.84
    POSITIVE LOGITS
    ↵↵
    0.57
    ,
    0.54
     lack
    0.47
    <eos>
    0.45
     z
    0.45
    <strong>
    0.45
     ko
    0.44
     sub
    0.43
     e
    0.42
     
    0.42
    Activations Density 0.284%

    No Known Activations