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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 5270
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental policies and their impacts

    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
     BorderSide
    -0.52
    ViewImports
    -0.52
    webElementXpaths
    -0.51
    Revenir
    -0.48
    ;*/
    -0.47
    OGND
    -0.47
     joão
    -0.45
    istoitu
    -0.40
    kegaard
    -0.40
     StringTokenizer
    -0.40
    POSITIVE LOGITS
     There
    1.81
     This
    1.67
     These
    1.66
     They
    1.64
     However
    1.63
     It
    1.57
     The
    1.57
     Although
    1.55
     When
    1.54
     If
    1.49
    Activations Density 2.052%

    No Known Activations