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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 50982
    Prev
    Next
    INDEX
    Explanations

    expressions of shame or related sentiments

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

    shame, shameful, ashamed, shameless

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jws
    -0.45
     Roost
    -0.44
    はじめに
    -0.43
     Plano
    -0.42
     cutout
    -0.42
     Clipper
    -0.42
     Uranus
    -0.42
     във
    -0.41
     bouquet
    -0.41
    ocu
    -0.41
    POSITIVE LOGITS
     Shame
    2.03
    Shame
    2.02
    shame
    1.94
     shame
    1.91
     honte
    1.38
     shameful
    1.30
     shaming
    1.27
     ashamed
    1.16
     vergüenza
    1.09
     shameless
    0.86
    Activations Density 0.004%

    No Known Activations