© 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. 39-GEMMASCOPE-RES-16K
    11. 4404
    Prev
    Next
    INDEX
    Explanations

    instances of personal pronouns, particularly first-person

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.51
    httphttps
    -0.44
    lidays
    -0.42
    Tig
    -0.42
    JNIEnv
    -0.41
    MessageTagHelper
    -0.40
    PLING
    -0.40
    helfen
    -0.40
    DockStyle
    -0.39
    +:+
    -0.39
    POSITIVE LOGITS
     guess
    1.07
     Guess
    0.81
    guess
    0.79
     suppose
    0.77
     mean
    0.75
    Guess
    0.71
     think
    0.64
     guesses
    0.57
     supposes
    0.49
     Suppose
    0.48
    Activations Density 0.274%

    No Known Activations