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. 14371
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and settings

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

    Locations such as buildings or rooms

    np_acts-logits-general · gemini-2.0-flash

    places and structures

    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
    Organisateur
    -0.46
    signature
    -0.45
    bukaan
    -0.44
     inversión
    -0.42
    verständlich
    -0.41
     całkow
    -0.41
     Schwester
    -0.40
     verdaderamente
    -0.40
     Isidro
    -0.40
     conformidad
    -0.39
    POSITIVE LOGITS
    SharedDtor
    0.60
    httphttps
    0.49
     ThemeData
    0.49
    mybatisplus
    0.45
     useDispatch
    0.43
    ніципалі
    0.43
    NameInMap
    0.43
    styleUrls
    0.43
    Aiheesta
    0.42
     $_"
    0.41
    Activations Density 0.330%

    No Known Activations