© 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. 31-GEMMASCOPE-RES-16K
    11. 9839
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to metrics and graphics

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

    words ending in "-atic" or "-ic" that are part of technical or formal terminology.

    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
     uſe
    -0.46
     juſ
    -0.45
     deſt
    -0.45
     ſtre
    -0.43
     ſer
    -0.41
     ſtand
    -0.40
     tranſ
    -0.39
     ſever
    -0.39
     pleaſure
    -0.38
    eſt
    -0.37
    POSITIVE LOGITS
    ally
    1.02
    ALLY
    0.84
    ially
    0.71
    tic
    0.63
    entric
    0.59
    ic
    0.59
    ated
    0.57
    ities
    0.55
    omic
    0.54
    cally
    0.53
    Activations Density 0.669%

    No Known Activations