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. 0-GEMMASCOPE-RES-16K
    6. 2589
    Prev
    Next
    INDEX
    Explanations

    function and variable declarations in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Erwachsenen
    -0.53
     alfombra
    -0.53
     posesión
    -0.52
     disposiciones
    -0.52
     oscuridad
    -0.52
     contemporánea
    -0.49
     amerikanischen
    -0.49
     solidaridad
    -0.49
     maravillas
    -0.48
     cooperación
    -0.48
    POSITIVE LOGITS
     invokingState
    0.89
     InputDecoration
    0.84
     =[]
    0.82
     )$
    0.81
     =-\
    0.81
     '\\;'
    0.81
     intStringLen
    0.80
     ProtoMessage
    0.79
     ]);
    0.78
     SafeArea
    0.78
    Activations Density 1.249%

    No Known Activations