© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 11083
    Prev
    Next
    INDEX
    Explanations

    terms related to health and environmental issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amerikanischer
    -0.64
     varandra
    -0.63
     tevens
    -0.58
    AxisAlignment
    -0.56
     större
    -0.55
     allmän
    -0.54
     egna
    -0.54
     autorité
    -0.53
     soin
    -0.52
     bestaande
    -0.51
    POSITIVE LOGITS
     thing
    1.27
     issue
    1.26
     phenomenon
    1.17
     fiasco
    1.16
     controversy
    1.15
     debate
    1.14
     craze
    1.14
     debacle
    1.13
     concept
    1.07
     saga
    1.05
    Activations Density 0.749%

    No Known Activations