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. 33-GEMMASCOPE-RES-16K
    6. 8082
    Prev
    Next
    INDEX
    Explanations

    terms related to software features and functionalities

    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
     considérons
    -0.42
     étoit
    -0.42
     kepentingan
    -0.39
     hänen
    -0.39
    berdayakan
    -0.38
     tehd
    -0.38
    
    -0.37
     Summe
    -0.37
     leão
    -0.37
     fakty
    -0.37
    POSITIVE LOGITS
     automatic
    1.02
     ability
    0.94
     auto
    0.89
     optional
    0.87
     customizable
    0.86
     advanced
    0.84
    automatic
    0.81
     Automatic
    0.79
    Ability
    0.79
     Ability
    0.79
    Activations Density 0.809%

    No Known Activations