© 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. 23-GEMMASCOPE-RES-16K
    6. 9796
    Prev
    Next
    INDEX
    Explanations

    specific keywords and terms related to technology and programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.80
     يتيمه
    -0.77
     فريبيس
    -0.77
     المعيارى
    -0.75
    __(/*!
    -0.75
     CreateTagHelper
    -0.74
    OGND
    -0.73
    IntoConstraints
    -0.70
     الحره
    -0.69
    出版年
    -0.69
    POSITIVE LOGITS
    ja
    0.33
    </strong>
    0.31
    ”.
    0.31
    1
    0.31
    ".
    0.30
    <eos>
    0.28
    http
    0.28
    <strong>
    0.28
    ).
    0.28
    ​
    0.27
    Activations Density 0.439%

    No Known Activations