© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 335
    Prev
    Next
    INDEX
    Explanations

    terms related to affirmative action and socioeconomic disparities

    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
     myſelf
    -0.82
     houſe
    -0.80
     Theſe
    -0.78
     Monfieur
    -0.77
     Houſe
    -0.73
     Diſ
    -0.73
     pleaſure
    -0.72
     faſt
    -0.72
     ſtate
    -0.72
     Reſ
    -0.71
    POSITIVE LOGITS
     to
    0.75
     or
    0.74
     and
    0.73
     versus
    0.60
     nonetheless
    0.51
     rather
    0.51
     nevertheless
    0.50
     vs
    0.49
    tagHelperRunner
    0.48
     through
    0.47
    Activations Density 0.400%

    No Known Activations