© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 14953
    Prev
    Next
    INDEX
    Explanations

    curly brackets and their associated contents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    LaTeX mathematical environment closing tags, particularly `\end{aligned}` and `\end{matrix}`.

    oai_token-act-pair · claude-4-5-haikuTriggered by @areeb0102
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     /*#__
    -0.34
     alike
    -0.28
     AssemblyCulture
    -0.27
     etc
    -0.26
     nuns
    -0.26
    さ
    -0.26
     typelib
    -0.26
    റ്
    -0.25
    _-
    -0.25
     insofar
    -0.25
    POSITIVE LOGITS
    ’
    0.78
    mathrm
    0.69
     deschis
    0.68
    bibfnamefont
    0.68
    '
    0.67
    ſelben
    0.66
     brinquedo
    0.66
     fashiola
    0.65
     initWithFrame
    0.65
     ſeinem
    0.65
    Activations Density 0.269%

    No Known Activations