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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8794
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to migration, transfer, and transition

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

    moving or changing

    np_acts-logits-general · gemini-2.0-flash

    change and movement

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Bogdan
    -0.48
    tanleria
    -0.48
     Савезне
    -0.48
     समीक्षाएं
    -0.45
     Minne
    -0.43
    彿
    -0.42
     صوتيه
    -0.41
    MENAFN
    -0.40
    esgue
    -0.40
    IGraphics
    -0.39
    POSITIVE LOGITS
     pindah
    0.84
     transitioning
    0.83
     shift
    0.82
     transfer
    0.82
     switching
    0.82
     transitioned
    0.82
     transferred
    0.80
     conversion
    0.79
     siir
    0.79
     Übergang
    0.79
    Activations Density 0.448%

    No Known Activations