© 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. 8059
    Prev
    Next
    INDEX
    Explanations

    negations and expressions of lack

    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
    exitRule
    -0.64
     springfox
    -0.61
    InputBorder
    -0.60
     Nye
    -0.60
    hous
    -0.57
     τὰ
    -0.56
    ALSE
    -0.56
    ContentAlignment
    -0.55
     Cora
    -0.54
     antar
    -0.54
    POSITIVE LOGITS
     didn
    2.71
    didn
    2.36
     Didn
    2.34
    Didn
    2.20
     DIDN
    2.00
     didnt
    1.84
     wasn
    1.76
     hadn
    1.70
     did
    1.67
     weren
    1.64
    Activations Density 0.094%

    No Known Activations