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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15140
    Prev
    Next
    INDEX
    Explanations

    references to numerical data and arrangements related to shelf organization

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

    Hexadecimal code

    np_acts-logits-general · gemini-2.0-flash

    shelf numbers

    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
     Kochen
    -0.28
     ComVisible
    -0.27
    ❉
    -0.26
     Савезне
    -0.26
     olsun
    -0.25
     Jesucristo
    -0.24
    verket
    -0.24
    couvrez
    -0.24
    NSIndexPath
    -0.24
    direktor
    -0.23
    POSITIVE LOGITS
    同じく
    0.70
    ValueStyle
    0.66
     ebenfalls
    0.66
    それも
    0.65
     TAMBÉM
    0.64
     $_"
    0.64
    こちらも
    0.63
     Waſſer
    0.61
     zwiſchen
    0.60
     ſich
    0.60
    Activations Density 1.399%

    No Known Activations