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. 9766
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components in programming

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

    Code snippets and programming-related terms

    np_acts-logits-general · gemini-2.0-flash

    UI layout and initialization

    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
     tartalomajánló
    -0.68
     kasarigan
    -0.67
    URLException
    -0.66
    Personendaten
    -0.55
    OGND
    -0.54
    HostException
    -0.54
    StoreMessageInfo
    -0.53
    Autoritní
    -0.53
     '\\;'
    -0.53
     otomatig
    -0.52
    POSITIVE LOGITS
     defaultstate
    0.45
    cheinend
    0.37
    argout
    0.35
    Aiheesta
    0.35
    EnableWeb
    0.33
     morire
    0.32
     dejamos
    0.31
    setupUi
    0.30
     indications
    0.30
     Del
    0.30
    Activations Density 0.071%

    No Known Activations