Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15603
    Prev
    Next
    INDEX
    Explanations

    occurrences of social dynamics and group interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tė
    -0.54
     desnuda
    -0.53
     dieťa
    -0.49
     Begründung
    -0.48
     dziecko
    -0.48
     zijne
    -0.48
     gafas
    -0.46
     isolato
    -0.44
     mijne
    -0.44
     Beobachtung
    -0.44
    POSITIVE LOGITS
     collectively
    0.67
    全員
    0.66
     protoimpl
    0.64
    脚注の使い方
    0.64
     resourceCulture
    0.64
    Their
    0.63
    their
    0.61
     CURIAM
    0.60
     Their
    0.59
     الرياضيه
    0.59
    Activations Density 1.361%

    No Known Activations