© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105668
    Prev
    Next
    INDEX
    Explanations

    components related to documents and their online availability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     tac
    -0.44
    createServer
    -0.42
     Creatures
    -0.42
     smer
    -0.41
    riders
    -0.41
    Sabato
    -0.41
    !*\
    -0.41
     APPLICATIONS
    -0.41
    Capítulo
    -0.40
    riding
    -0.40
    POSITIVE LOGITS
     Administrativna
    0.50
     sanitarias
    0.49
    rawDesc
    0.47
    rungsseite
    0.47
     externi
    0.46
     dostęp
    0.46
     reproduced
    0.45
     presença
    0.45
     prič
    0.45
    msgTypes
    0.44
    Activations Density 0.011%

    No Known Activations