© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 11002
    Prev
    Next
    INDEX
    Explanations

    references to musical elements and instrumentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    matchCondition
    -0.42
     ProtoMessage
    -0.41
    tonsoft
    -0.38
     Harm
    -0.38
     NavController
    -0.36
     avião
    -0.35
    contentLoaded
    -0.35
    Harm
    -0.35
    ربای
    -0.35
    الإنجليزية
    -0.34
    POSITIVE LOGITS
     drum
    1.56
     drums
    1.41
     drumming
    1.38
     Drum
    1.34
    drum
    1.30
    Drum
    1.28
     drummer
    1.21
     Drums
    1.20
    drums
    1.17
     DRUM
    1.15
    Activations Density 0.106%

    No Known Activations