© 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. 14-GEMMASCOPE-RES-16K
    11. 6251
    Prev
    Next
    INDEX
    Explanations

    terms related to numerical measurements and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.50
    enumii
    -0.41
    Referencie
    -0.38
     AttributeSet
    -0.36
     Pristupljeno
    -0.35
     asesinado
    -0.35
     nettement
    -0.34
    MemoryWarning
    -0.34
     arrivé
    -0.33
     actitudes
    -0.33
    POSITIVE LOGITS
     CreateTagHelper
    0.83
    tagHelperRunner
    0.62
     permeable
    0.59
     للمعارف
    0.57
    tvguidetime
    0.57
    tamaris
    0.56
     betweenstory
    0.53
    featureID
    0.51
     useCallback
    0.51
     Soluble
    0.51
    Activations Density 0.488%

    No Known Activations