© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 14459
    Prev
    Next
    INDEX
    Explanations

    structured data representations, particularly those related to key-value pairs and metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 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
    ViewFeatures
    -1.33
     iſt
    -1.31
     SwitchCompat
    -1.30
     photolibrary
    -1.28
    +#+#
    -1.27
    ValueStyle
    -1.24
     itſelf
    -1.23
     pleaſure
    -1.22
     Majefty
    -1.21
    ########.
    -1.20
    POSITIVE LOGITS
     
    1.08
    ↵↵
    0.94
     (
    0.92
     "
    0.88
    :
    0.87
    ,
    0.81
     R
    0.80
    ↵
    0.78
     A
    0.78
    .
    0.78
    Activations Density 1.079%

    No Known Activations