Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 67577
    Prev
    Next
    INDEX
    Explanations

    elements related to tone, atmosphere, and emotional quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     NSCoder
    -0.69
     BrowserModule
    -0.67
    ésus
    -0.65
    ########.
    -0.55
    autorest
    -0.55
    httphttps
    -0.54
    BrowserModule
    -0.53
    dafx
    -0.53
    opha
    -0.51
    ſelf
    -0.50
    POSITIVE LOGITS
     vibe
    0.91
     Stimmung
    0.78
     atmosphere
    0.78
     ambiance
    0.78
     ambience
    0.76
    vibe
    0.75
     mood
    0.74
     vibes
    0.71
     atmosfera
    0.69
    雰囲気
    0.66
    Activations Density 0.025%

    No Known Activations