© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 2156
    Prev
    Next
    INDEX
    Explanations

    numeric values, particularly sequences, citations, and references in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.74
    الدراسه
    -0.73
    Tikang
    -0.69
    +:+
    -0.66
    UnitTesting
    -0.66
     queſta
    -0.65
    afficheront
    -0.65
     BoxFit
    -0.64
    出版年
    -0.63
    Autoritní
    -0.63
    POSITIVE LOGITS
     Constitucional
    0.42
     Independencia
    0.42
     mempertahankan
    0.34
     hidupnya
    0.32
     constitucional
    0.32
     operativos
    0.32
     sintético
    0.31
     Investigación
    0.31
     mariée
    0.31
     varones
    0.31
    Activations Density 0.830%

    No Known Activations