© 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. 28-GEMMASCOPE-RES-16K
    6. 3673
    Prev
    Next
    INDEX
    Explanations

    keywords associated with testing, data management, and legal references

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

    Code, methods, properties, or datasets

    np_acts-logits-general · gemini-2.0-flash

    technical terms and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     moindre
    -0.31
     ibunya
    -0.30
     istrinya
    -0.29
     Wassers
    -0.29
     rumahnya
    -0.29
     matahari
    -0.29
     dieną
    -0.28
     orejas
    -0.28
     lesquels
    -0.27
     anaknya
    -0.27
    POSITIVE LOGITS
    MigrationBuilder
    1.13
     ब्रेकडाउन
    1.03
    tagHelperRunner
    1.01
     betweenstory
    1.01
    <unused68>
    1.00
    <unused79>
    0.99
    [@BOS@]
    0.99
    <unused14>
    0.99
    <unused28>
    0.99
    <unused52>
    0.99
    Activations Density 1.452%

    No Known Activations