© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 87171
    Prev
    Next
    INDEX
    Explanations

    concepts surrounding dignity and respect for individuals

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

    inherent worth and respect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     geçir
    -0.46
     Canarias
    -0.44
     Anhäng
    -0.44
    jutnya
    -0.43
    FileData
    -0.43
     favourites
    -0.42
     насе
    -0.42
     plans
    -0.42
     run
    -0.42
    Followers
    -0.42
    POSITIVE LOGITS
     dignity
    1.24
     Dignity
    1.18
     dignidad
    1.06
    dign
    1.05
     dignité
    1.05
     dignified
    1.02
     Dign
    0.90
     dign
    0.79
    AnchorStyles
    0.66
     digna
    0.64
    Activations Density 0.004%

    No Known Activations