Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 8989
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 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
     generalizations
    -0.58
    oté
    -0.51
    cino
    -0.51
     discontinuities
    -0.51
     Darío
    -0.51
    emas
    -0.51
     Maxi
    -0.50
     Hiper
    -0.50
     '/':
    -0.50
    ("-");
    -0.49
    POSITIVE LOGITS
     Myself
    1.04
     Yourself
    0.96
     ourselves
    0.93
     YOURSELF
    0.91
     yourself
    0.90
    selves
    0.90
    Myself
    0.89
    myself
    0.89
     myself
    0.87
     sendiri
    0.86
    Activations Density 0.217%

    No Known Activations