Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 12479
    Prev
    Next
    INDEX
    Explanations

    specific terms related to traditional instruments and cultural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 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
     esternos
    -0.82
    PerformLayout
    -0.73
    HasForeignKey
    -0.73
     @"/
    -0.54
     newOwner
    -0.52
    tehenden
    -0.52
     defaultstate
    -0.52
    ově
    -0.51
    äť
    -0.50
    waitUntil
    -0.50
    POSITIVE LOGITS
    replaced
    0.50
    izziness
    0.50
    Verein
    0.48
     UserDetails
    0.48
     alma
    0.48
    lan
    0.47
    lane
    0.47
     ed
    0.46
    แล
    0.46
     Edin
    0.45
    Activations Density 0.083%

    No Known Activations