© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3814
    Prev
    Next
    INDEX
    Explanations

    phrases related to social and racial inequalities

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

    racist, inflammatory language targeting specific racial or ethnic groups.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    richTextPanel
    -0.67
    expandindo
    -0.61
     Exacts
    -0.50
    RTHOOK
    -0.50
    Autoritní
    -0.45
    StreetMap
    -0.41
     determinations
    -0.41
    Rüyada
    -0.40
    исленность
    -0.40
     $_"
    -0.40
    POSITIVE LOGITS
     coward
    0.48
     trash
    0.46
     idiotic
    0.46
    rungsseite
    0.45
     idiot
    0.45
     wanna
    0.45
     scum
    0.44
     karma
    0.44
     garbage
    0.42
     immature
    0.42
    Activations Density 0.303%

    No Known Activations