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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 5976
    Prev
    Next
    INDEX
    Explanations

    terms related to eligibility in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
     uska
    -0.45
    WriteBarrier
    -0.44
    Portale
    -0.44
     '\\;'
    -0.42
    NUMX
    -0.42
    RTEE
    -0.42
    PyExc
    -0.41
     vPvB
    -0.41
    addCriterion
    -0.41
    setObjectName
    -0.41
    POSITIVE LOGITS
     qualifying
    0.82
     eligible
    0.75
    Qual
    0.75
     qualify
    0.71
     losses
    0.69
     qualifies
    0.68
    eligible
    0.68
    qual
    0.65
     premier
    0.60
     QUAL
    0.59
    Activations Density 0.129%

    No Known Activations