© 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. 22-GEMMASCOPE-RES-16K
    11. 4138
    Prev
    Next
    INDEX
    Explanations

    causal relationships emphasized by the word "because"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MethodManager
    -0.57
     doInBackground
    -0.53
    tableFuture
    -0.51
    ModelSerializer
    -0.48
    =$?
    -0.48
    MLLoader
    -0.48
    AnimationsModule
    -0.47
     jPanel
    -0.47
    glEnd
    -0.46
    isContained
    -0.46
    POSITIVE LOGITS
     its
    0.54
     although
    0.48
     obwohl
    0.47
     kerana
    0.40
     it
    0.40
     having
    0.40
     fiind
    0.40
     despite
    0.39
     eftersom
    0.38
    Nunca
    0.38
    Activations Density 0.505%

    No Known Activations