© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 13038
    Prev
    Next
    INDEX
    Explanations

    phrases expressing belief in specific concepts or ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    multer
    -0.56
     playmobil
    -0.49
     محفوظة
    -0.48
     cop
    -0.48
     OTT
    -0.46
     porn
    -0.46
     likely
    -0.46
    罷
    -0.46
     barrage
    -0.45
    Likely
    -0.45
    POSITIVE LOGITS
    AnchorStyles
    0.48
    fficacy
    0.44
    UnknownFieldSet
    0.42
     believer
    0.42
    DllImport
    0.40
     faith
    0.39
     promouvoir
    0.39
    XmlEnum
    0.37
    /*
    0.37
     Teamwork
    0.37
    Activations Density 0.141%

    No Known Activations