© 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. 24-GEMMASCOPE-RES-16K
    11. 10203
    Prev
    Next
    INDEX
    Explanations

    terms related to file systems and data storage technologies

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

    SAN or replication technologies

    np_acts-logits-general · gemini-2.0-flash

    Xsan storage backup retention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intptr
    -0.79
    findpost
    -0.68
     defaultstate
    -0.67
    PerformLayout
    -0.64
    +#+#
    -0.58
     estekak
    -0.58
     insuffisamment
    -0.56
    ArgsConstructor
    -0.56
    OGND
    -0.56
    kuuta
    -0.54
    POSITIVE LOGITS
     tape
    0.67
     backup
    0.63
     replication
    0.63
    WriteBarrier
    0.61
    Tape
    0.60
    tape
    0.60
     Tape
    0.57
    flashdata
    0.57
     Replication
    0.57
    RetentionPolicy
    0.56
    Activations Density 0.272%

    No Known Activations