© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3243
    Prev
    Next
    INDEX
    Explanations

    concepts related to evolution and design

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

    This neuron appears to be activating on a highly diverse and seemingly unrelated set of tokens across different document types (philosophical discourse, Japanese media content, programming code, and economic articles), making it difficult to identify a single coherent pattern. However, examining the strongest activations reveals that the neu

    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
    出版年
    -0.72
     AssemblyTitle
    -0.54
    الدراسه
    -0.48
    Personendaten
    -0.47
     propOrder
    -0.47
    MIDDLEWARE
    -0.47
    stateProvider
    -0.46
    Життєпис
    -0.45
    Followers
    -0.44
     errorCode
    -0.43
    POSITIVE LOGITS
     typing
    0.42
     Luc
    0.41
    ApiModelProperty
    0.40
    mobileqq
    0.39
    댓
    0.37
     evolve
    0.36
    Luc
    0.36
     evolves
    0.35
     typed
    0.35
     Typing
    0.35
    Activations Density 0.099%

    No Known Activations