© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 39163
    Prev
    Next
    INDEX
    Explanations

    references to keys and their significance

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

    key, keys, or key points

    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
     doInBackground
    -0.50
    dą
    -0.44
    исленность
    -0.43
     câte
    -0.42
     cantit
    -0.41
    ppuden
    -0.41
    zusammen
    -0.40
    ainville
    -0.40
     فريبيس
    -0.38
     Bharat
    -0.38
    POSITIVE LOGITS
     keys
    0.79
    🔑
    0.75
     Schlüssel
    0.71
     GlobalKey
    0.69
    钥匙
    0.68
    HomeAsUpEnabled
    0.67
     getKey
    0.65
     KEYS
    0.64
     key
    0.63
    🗝
    0.63
    Activations Density 0.014%

    No Known Activations