© 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. 25-GEMMASCOPE-RES-16K
    11. 15112
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.71
     témoig
    -0.66
    Datuak
    -0.66
     ſondern
    -0.66
     Photocase
    -0.65
    <unused16>
    -0.65
    ThroughAttribute
    -0.65
    <unused52>
    -0.65
    <unused21>
    -0.64
    [@BOS@]
    -0.64
    POSITIVE LOGITS
     ,
    0.36
     ]
    0.35
    ↵
    0.35
     )
    0.34
     And
    0.34
    قایناق‌لار
    0.34
     Serrano
    0.33
    ']?>
    0.33
     =
    0.32
    ensuremath
    0.32
    Activations Density 4.570%

    No Known Activations