© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 2966
    Prev
    Next
    INDEX
    Explanations

    phrases indicating expected behavior or outcomes in a testing context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    المناصب
    -1.01
     '\\;'
    -0.94
    клопе
    -0.93
    (;;)
    -0.91
    WriteBarrier
    -0.89
    NUMX
    -0.88
    ]")]
    -0.88
    URLException
    -0.86
    '])){
    -0.85
     nonUne
    -0.84
    POSITIVE LOGITS
    should
    1.05
     should
    0.88
    Should
    0.85
     Should
    0.75
     SHOULD
    0.69
    assertThat
    0.64
     shouldn
    0.60
     must
    0.59
     might
    0.58
    may
    0.57
    Activations Density 0.045%

    No Known Activations