© 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. 31-GEMMASCOPE-RES-16K
    11. 2815
    Prev
    Next
    INDEX
    Explanations

    references to musical albums and their details

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

    This neuron is looking for album track listings and related metadata sections.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    лтамалар
    -0.58
    хьтан
    -0.53
    CloseOperation
    -0.53
     '\\;'
    -0.51
    IUrlHelper
    -0.50
     EconPapers
    -0.50
    WithIOException
    -0.50
    parsedMessage
    -0.49
    новниш
    -0.47
     pleaſure
    -0.46
    POSITIVE LOGITS
     track
    1.23
     tracks
    1.16
    track
    1.05
     Track
    1.01
    Track
    0.91
    tracks
    0.91
     TRACK
    0.91
     Tracks
    0.88
    TRACK
    0.81
    Tracks
    0.77
    Activations Density 0.129%

    No Known Activations