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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 4269
    Prev
    Next
    INDEX
    Explanations

    discussions about sexual orientation and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chloe
    -0.83
     Gabe
    -0.79
    Chloe
    -0.79
     Raven
    -0.78
     Kane
    -0.78
     Bryan
    -0.75
    \{\\
    -0.71
    Raven
    -0.71
    Gabe
    -0.71
     Metric
    -0.70
    POSITIVE LOGITS
     Barbour
    0.99
     RC
    0.81
     Nokia
    0.74
     rc
    0.73
     Parson
    0.72
     Gui
    0.71
     NOK
    0.70
    NOK
    0.70
    Rc
    0.69
     Gué
    0.68
    Activations Density 1.690%

    No Known Activations