© 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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11969
    Prev
    Next
    INDEX
    Explanations

    concepts related to teaching independence in young children

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     المعيارى
    -0.58
    reportWebVitals
    -0.57
     AssemblyCompany
    -0.56
     BoxDecoration
    -0.54
    lorette
    -0.54
    TryDecodeAsNil
    -0.52
     ProtoMessage
    -0.51
    UnifiedTopology
    -0.50
    Hochspringen
    -0.50
     protoimpl
    -0.49
    POSITIVE LOGITS
     learning
    0.40
     classroom
    0.38
     learn
    0.38
    Learn
    0.36
     aprendizagem
    0.36
     psych
    0.35
    tagHelperRunner
    0.35
     daily
    0.35
     child
    0.34
     learner
    0.33
    Activations Density 0.100%

    No Known Activations