© 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. 3341
    Prev
    Next
    INDEX
    Explanations

    instances of the word "possible" and its context in statements

    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
     aveug
    -0.49
     vermelhas
    -0.47
     aprendido
    -0.46
    mær
    -0.45
    uParam
    -0.45
     TÉCN
    -0.44
    ohjel
    -0.43
     programación
    -0.43
     Weih
    -0.42
     autoestima
    -0.42
    POSITIVE LOGITS
    possibility
    0.87
     Possibility
    0.86
     Possible
    0.84
    Possibility
    0.82
     possib
    0.80
     possibility
    0.79
    possible
    0.77
    Possible
    0.75
    TargetException
    0.75
    POSSIBLE
    0.72
    Activations Density 0.163%

    No Known Activations