© 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. 33-GEMMASCOPE-RES-16K
    11. 11625
    Prev
    Next
    INDEX
    Explanations

    specific coding or technical terms related to computing systems and networks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     desmotivaciones
    -0.62
    berdayakan
    -0.54
     conferencias
    -0.54
     invitaciones
    -0.52
     burbujas
    -0.50
     Wikiseite
    -0.50
     näytte
    -0.48
    PERATURE
    -0.47
     another
    -0.47
     mijne
    -0.47
    POSITIVE LOGITS
     Administrativna
    0.68
    AP
    0.59
    AC
    0.59
    BC
    0.58
    Ob
    0.57
    IB
    0.57
    IntoConstraints
    0.56
    FC
    0.55
    IM
    0.54
    AB
    0.54
    Activations Density 1.391%

    No Known Activations