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. 9-GEMMASCOPE-RES-16K
    6. 3249
    Prev
    Next
    INDEX
    Explanations

    numerical data and quantifiable values

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

    Tokens starting with "45"

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -0.52
     useAppContext
    -0.46
    ┗
    -0.44
    Lek
    -0.43
     estekak
    -0.43
     BK
    -0.43
                                
    -0.43
     leksikon
    -0.43
    IU
    -0.42
    achios
    -0.42
    POSITIVE LOGITS
     wikipagina
    0.63
     damskie
    0.63
     antidesliz
    0.62
     baweł
    0.60
     réfugi
    0.60
     enfans
    0.60
    ſelves
    0.59
     vlasy
    0.57
     semula
    0.57
     cromado
    0.57
    Activations Density 0.547%

    No Known Activations