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. 3-GEMMASCOPE-RES-16K
    6. 1391
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental topics and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.65
     fáciles
    -0.63
     aéri
    -0.62
     casada
    -0.59
    tagHelperRunner
    -0.58
     paire
    -0.56
     Bounce
    -0.56
    Surgical
    -0.56
     rápidas
    -0.56
     jugos
    -0.55
    POSITIVE LOGITS
     environmental
    2.71
     Environmental
    2.57
    Environmental
    2.41
    environmental
    2.22
     ENVIRONMENTAL
    2.20
    ENVIRONMENTAL
    2.06
     environmentally
    1.83
     Environ
    1.77
     Umwel
    1.71
     ambiental
    1.71
    Activations Density 0.078%

    No Known Activations