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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 58825
    Prev
    Next
    INDEX
    Explanations

    references to episodes in a series or show

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

    episode

    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
     financeira
    -0.63
     algemene
    -0.55
     braços
    -0.52
     FirebaseAuth
    -0.51
    🏼
    -0.50
     braço
    -0.49
    databind
    -0.49
     ağaç
    -0.48
     pintor
    -0.47
     matemáticas
    -0.47
    POSITIVE LOGITS
     episode
    1.30
     episodes
    1.27
     Episode
    1.13
     Episodes
    1.09
    Episode
    1.09
    episode
    1.07
    Episodes
    1.03
    episodes
    0.97
     EPISODE
    0.95
    pisode
    0.93
    Activations Density 0.007%

    No Known Activations