© 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. 13421
    Prev
    Next
    INDEX
    Explanations

    concepts related to trouble or problematic situations

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

    phrases expressing that someone has gotten into or caused trouble or problems.

    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
     ErrIntOverflow
    -0.41
    Референце
    -0.36
     باخ
    -0.35
    Kjelder
    -0.35
    참고
    -0.35
    ])));
    -0.34
    gamesh
    -0.34
    chomp
    -0.34
    enterOuterAlt
    -0.34
    TestingModule
    -0.34
    POSITIVE LOGITS
     trouble
    2.42
    trouble
    2.05
     troubles
    1.99
     Trouble
    1.99
    Trouble
    1.93
     Troubles
    1.57
    trou
    1.41
    麻烦
    1.32
    Trou
    1.31
     TRO
    1.26
    Activations Density 0.297%

    No Known Activations