© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 65311
    Prev
    Next
    INDEX
    Explanations

    elements associated with specific cultural or geographical characteristics

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

    atmosphere and feeling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ̈́
    -0.41
    Personendaten
    -0.38
    뀜
    -0.37
     Вікіпе
    -0.36
     smtplib
    -0.35
     SafeMath
    -0.34
    ResumeLayout
    -0.33
     Theſe
    -0.33
     IndexError
    -0.32
    RTEX
    -0.32
    POSITIVE LOGITS
     feeling
    1.89
     feel
    1.74
    feeling
    1.63
     vibe
    1.56
    feel
    1.55
     Feeling
    1.49
     FEEL
    1.45
    Feeling
    1.45
     vibes
    1.41
     gevoel
    1.40
    Activations Density 0.076%

    No Known Activations