© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4310
    Prev
    Next
    INDEX
    Explanations

    references to one-way tickets and related travel arrangements

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

    the phrase "one way" in various contexts.

    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
     appName
    -0.43
     dil
    -0.42
     Kie
    -0.38
     acquitted
    -0.37
    nador
    -0.37
     dilution
    -0.37
     Vic
    -0.35
    الحياه
    -0.35
    TagName
    -0.35
    OfBirth
    -0.35
    POSITIVE LOGITS
     unilateral
    1.55
     unid
    1.38
     unilaterally
    1.32
     asymmetric
    1.05
     asymmetrical
    1.05
    unid
    1.01
     unil
    1.01
     asymmetry
    0.97
     One
    0.94
    ilateral
    0.94
    Activations Density 0.302%

    No Known Activations