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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12559
    Prev
    Next
    INDEX
    Explanations

    references to psychological and ethical considerations surrounding societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Adjectives after conjunctions

    np_acts-logits-general · gemini-2.0-flash

    adjectives describing qualities or domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    乱
    -0.40
    ものです
    -0.37
     comprim
    -0.36
    exitRule
    -0.35
     smartphones
    -0.34
     wheels
    -0.33
     bross
    -0.33
    absent
    -0.33
     rezer
    -0.33
     ALTERN
    -0.32
    POSITIVE LOGITS
     cultural
    0.69
     sociological
    0.68
     logistical
    0.63
    aarrggbb
    0.63
     political
    0.61
     يتيمه
    0.60
     structural
    0.60
     psychological
    0.60
     climatic
    0.59
    ArgsConstructor
    0.59
    Activations Density 0.469%

    No Known Activations