© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 102647
    Prev
    Next
    INDEX
    Explanations

    phrases related to downloading games or software

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

    tell us about downloads

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    specie
    -0.51
    السكان
    -0.49
    новништво
    -0.48
    EFAULT
    -0.48
    tences
    -0.47
     فريبيس
    -0.47
    restle
    -0.47
    ListItemIcon
    -0.47
    mobili
    -0.44
     CreateTagHelper
    -0.43
    POSITIVE LOGITS
     noDo
    0.45
     ordinaire
    0.42
     nonUne
    0.36
     teórico
    0.35
     ordinaires
    0.35
     visuales
    0.34
    distribution
    0.34
     distribuidor
    0.34
     continúas
    0.34
    Distribution
    0.34
    Activations Density 0.018%

    No Known Activations