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. 20-GEMMASCOPE-RES-131K
    6. 86301
    Prev
    Next
    INDEX
    Explanations

    discussions related to social structure and cultural identity

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

    contrast between ideas

    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
     pleaſure
    -0.58
    +#+
    -0.57
    iſen
    -0.56
    edicated
    -0.56
     houſe
    -0.53
     $_"
    -0.53
     propOrder
    -0.53
    ſchen
    -0.51
     queſta
    -0.50
     محفوظة
    -0.50
    POSITIVE LOGITS
    帖最后由
    0.51
    GEBURTSDATUM
    0.51
    httphttps
    0.44
    不妨
    0.41
     Gegenstand
    0.41
     politie
    0.38
     Gegenstände
    0.38
     gegenwär
    0.37
     contexts
    0.37
     uitgenodigd
    0.36
    Activations Density 0.192%

    No Known Activations