© 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-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15420
    Prev
    Next
    INDEX
    Explanations

    template strings and variable interpolation syntax in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     faſt
    -0.70
     ſch
    -0.63
     Савезне
    -0.62
     houſe
    -0.59
    ChildScrollView
    -0.58
     Houſe
    -0.58
     ſta
    -0.57
     ſte
    -0.55
     Anſ
    -0.54
     newArray
    -0.51
    POSITIVE LOGITS
    ="<?=
    1.12
    ="<?=$
    0.91
    ="{{
    0.91
    "><?=
    0.75
    <?=
    0.69
    ="${
    0.65
    /#{
    0.63
     cref
    0.62
    (`${
    0.61
    ="<?
    0.59
    Activations Density 0.235%

    No Known Activations