© 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. 7597
    Prev
    Next
    INDEX
    Explanations

    conditional statements and checks related to data structures and variables

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

    conditional statements using comparison operators (like `==`, `!=`, `<>`) and logical conditions.

    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
     resourceCulture
    -0.66
    AutoScaleMode
    -0.48
    ArgumentParser
    -0.45
     Indirect
    -0.45
    saraba
    -0.43
    Indirect
    -0.43
    ⟬
    -0.43
    indirect
    -0.42
    ChildScrollView
    -0.42
    IUrlHelper
    -0.42
    POSITIVE LOGITS
     empty
    2.67
     Empty
    2.25
    empty
    2.16
    Empty
    2.09
     EMPTY
    1.98
     emptiness
    1.86
    EMPTY
    1.82
     blank
    1.72
     vacant
    1.71
    空
    1.70
    Activations Density 0.432%

    No Known Activations